font
Filter
×
2026
Deshmukh, Jayati; Yazdanpanah, Vahid; Stein, Sebastian; Ramchurn, Gopal
The triad of identity, trust and responsibility in multi-agent systems Proceedings Article
In: 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26), 2026.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Coordination, Ethics, Identity, Multiagent Systems, Norms, Responsibility, Trust
@inproceedings{soton509930,
title = {The triad of identity, trust and responsibility in multi-agent systems},
author = {Jayati Deshmukh and Vahid Yazdanpanah and Sebastian Stein and Gopal Ramchurn},
url = {https://eprints.soton.ac.uk/509930/},
year = {2026},
date = {2026-05-01},
booktitle = {25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26)},
abstract = {The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.},
keywords = {Artificial Intelligence, Coordination, Ethics, Identity, Multiagent Systems, Norms, Responsibility, Trust},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.
2025
Thavanesan, Navamayooran; Naiseh, Mohammad; Terol, Miguel; Rahman, Saqib Andrew; Hill, Samuel Luke; Parfitt, Charlotte; Walters, Zoë S; Ramchurn, Sarvapali; Markar, Sheraz; Owen, Richard; Maynard, Nick; Azim, Tayyaba; Belkatir, Zehor; Perez, Elvira Vallejos; McCord, Mimi; Underwood, Tim; Vigneswaran, Ganesh
The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system Journal Article
In: EClinicalMedicine, vol. 89, pp. 103527, 2025, (For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Decision support tool, machine learning, MDT, Multidisciplinary teams, Oesophageal cancer
@article{soton506614,
title = {The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system},
author = {Navamayooran Thavanesan and Mohammad Naiseh and Miguel Terol and Saqib Andrew Rahman and Samuel Luke Hill and Charlotte Parfitt and Zoë S Walters and Sarvapali Ramchurn and Sheraz Markar and Richard Owen and Nick Maynard and Tayyaba Azim and Zehor Belkatir and Elvira Vallejos Perez and Mimi McCord and Tim Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/506614/},
year = {2025},
date = {2025-09-01},
journal = {EClinicalMedicine},
volume = {89},
pages = {103527},
abstract = {ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>},
note = {For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.},
keywords = {Artificial Intelligence, Decision support tool, machine learning, MDT, Multidisciplinary teams, Oesophageal cancer},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>
2023
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J.; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, vol. 49, no. 11, 2023, (Publisher Copyright: © 2023 The Author(s)).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team
@article{soton479497b,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J. Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-11-01},
journal = {European Journal of Surgical Oncology},
volume = {49},
number = {11},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
© 2023 The Author(s)},
keywords = {Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub Response Miscellaneous
2023.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy
@misc{soton481740,
title = {AI large language models inquiry: TASHub Response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub response Miscellaneous
2023.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy
@misc{soton481740b,
title = {AI large language models inquiry: TASHub response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, 2023, (Publisher Copyright: copyright 2023 The Author(s)).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team
@article{soton479497,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-07-01},
journal = {European Journal of Surgical Oncology},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
copyright 2023 The Author(s)},
keywords = {Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
Krook, Joshua; McAuley, Derek; Anderson, Stuart; Downer, John; Winter, Peter; Ramchurn, Sarvapali D
AI Foundation Models: initial review, CMA Consultation, TAS Hub Response Miscellaneous
2023.
Links | BibTeX | Tags: Artificial Intelligence, Competition policy, featured_publication, Foundation Models, Large Language Models, markets
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
publisher = {University of Southampton},
keywords = {Artificial Intelligence, Competition policy, featured_publication, Foundation Models, Large Language Models, markets},
pubstate = {published},
tppubtype = {misc}
}
Krook, Joshua; Downer, John; Winter, Peter; Williams, Jennifer; Ives, Jonathan; Bratu, Roxana; Sheir, Stephanie; Williams, Robin; Anderson, Stuart; Li, Phoebe; Ramamoorthy, Subramanian; Ramchurn, Sarvapali
AI regulation: a pro-innovation approach ? policy proposals: TASHub Response Miscellaneous
2023.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Consultation, innovation, Regulation, Trustworthy Autonomous Systems
@misc{soton478329,
title = {AI regulation: a pro-innovation approach ? policy proposals: TASHub Response},
author = {Joshua Krook and John Downer and Peter Winter and Jennifer Williams and Jonathan Ives and Roxana Bratu and Stephanie Sheir and Robin Williams and Stuart Anderson and Phoebe Li and Subramanian Ramamoorthy and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478329/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
abstract = {Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence},
keywords = {Artificial Intelligence, Consultation, innovation, Regulation, Trustworthy Autonomous Systems},
pubstate = {published},
tppubtype = {misc}
}
Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence
2022
Yazdanpanah, Vahid; Gerding, Enrico; Stein, Sebastian; Dastani, Mehdi; Jonker, Catholijn M; Norman, Timothy; Ramchurn, Sarvapali
Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities Journal Article
In: AI & Society, 2022.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Citizen-Centric AI Systems, human-agent collectives, Human-Centred AI, Multiagent Responsibility Reasoning, Multiagent Systems, Trustworthy Autonomous Systems
@article{soton471971,
title = {Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities},
author = {Vahid Yazdanpanah and Enrico Gerding and Sebastian Stein and Mehdi Dastani and Catholijn M Jonker and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/471971/},
year = {2022},
date = {2022-11-01},
journal = {AI & Society},
abstract = {Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.},
keywords = {Artificial Intelligence, Citizen-Centric AI Systems, human-agent collectives, Human-Centred AI, Multiagent Responsibility Reasoning, Multiagent Systems, Trustworthy Autonomous Systems},
pubstate = {published},
tppubtype = {article}
}
Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.
Soorati, Mohammad Divband; Gerding, Enrico; Marchioni, Enrico; Naumov, Pavel; Norman, Timothy; Ramchurn, Sarvapali; Rastegari, Baharak; Sobey, Adam; Stein, Sebastian; Tarapore, Danesh; Yazdanpanah, Vahid; Zhang, Jie
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems Journal Article
In: AI Communications, 2022.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Distributed Artificial Intelligence, Intelligent Agents, Multiagent Systems, Trustworthy Autonomous Systems
@article{soton467975,
title = {From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems},
author = {Mohammad Divband Soorati and Enrico Gerding and Enrico Marchioni and Pavel Naumov and Timothy Norman and Sarvapali Ramchurn and Baharak Rastegari and Adam Sobey and Sebastian Stein and Danesh Tarapore and Vahid Yazdanpanah and Jie Zhang},
url = {https://eprints.soton.ac.uk/467975/},
year = {2022},
date = {2022-07-01},
journal = {AI Communications},
abstract = {The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.},
keywords = {Artificial Intelligence, Distributed Artificial Intelligence, Intelligent Agents, Multiagent Systems, Trustworthy Autonomous Systems},
pubstate = {published},
tppubtype = {article}
}
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.
2021
Ramchurn, Sarvapali; Middleton, Stuart; McAuley, Derek; Webb, Helena; Hyde, Richard; Lisinska, Justyna
A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee Technical Report
no. 10.18742/pub01-060, 2021.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Online Harms
@techreport{soton451428,
title = {A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee},
author = {Sarvapali Ramchurn and Stuart Middleton and Derek McAuley and Helena Webb and Richard Hyde and Justyna Lisinska},
url = {https://eprints.soton.ac.uk/451428/},
year = {2021},
date = {2021-09-01},
number = {10.18742/pub01-060},
abstract = {This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.},
keywords = {Artificial Intelligence, Online Harms},
pubstate = {published},
tppubtype = {techreport}
}
This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.
Ramchurn, Sarvapali; Stein, Sebastian; Jennings, Nicholas R
Trustworthy human-AI partnerships Journal Article
In: iScience, vol. 24, no. 8, 2021.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Human-Computer Interaction, Sociology
@article{soton450597,
title = {Trustworthy human-AI partnerships},
author = {Sarvapali Ramchurn and Sebastian Stein and Nicholas R Jennings},
url = {https://eprints.soton.ac.uk/450597/},
year = {2021},
date = {2021-08-01},
journal = {iScience},
volume = {24},
number = {8},
abstract = {In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.},
keywords = {Artificial Intelligence, Human-Computer Interaction, Sociology},
pubstate = {published},
tppubtype = {article}
}
In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.
Beal, Ryan James; Middleton, Stuart; Norman, Timothy; Ramchurn, Sarvapali
Combining machine learning and human experts to predict match outcomes in football: A baseline model Proceedings Article
In: The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21), 2021.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Natural Language Processing
@inproceedings{soton445607,
title = {Combining machine learning and human experts to predict match outcomes in football: A baseline model},
author = {Ryan James Beal and Stuart Middleton and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445607/},
year = {2021},
date = {2021-02-01},
booktitle = {The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21)},
abstract = {In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.},
keywords = {Artificial Intelligence, Natural Language Processing},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
1.
Deshmukh, Jayati; Yazdanpanah, Vahid; Stein, Sebastian; Ramchurn, Gopal
The triad of identity, trust and responsibility in multi-agent systems Proceedings Article
In: 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26), 2026.
@inproceedings{soton509930,
title = {The triad of identity, trust and responsibility in multi-agent systems},
author = {Jayati Deshmukh and Vahid Yazdanpanah and Sebastian Stein and Gopal Ramchurn},
url = {https://eprints.soton.ac.uk/509930/},
year = {2026},
date = {2026-05-01},
booktitle = {25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26)},
abstract = {The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.
2.
Thavanesan, Navamayooran; Naiseh, Mohammad; Terol, Miguel; Rahman, Saqib Andrew; Hill, Samuel Luke; Parfitt, Charlotte; Walters, Zoë S; Ramchurn, Sarvapali; Markar, Sheraz; Owen, Richard; Maynard, Nick; Azim, Tayyaba; Belkatir, Zehor; Perez, Elvira Vallejos; McCord, Mimi; Underwood, Tim; Vigneswaran, Ganesh
The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system Journal Article
In: EClinicalMedicine, vol. 89, pp. 103527, 2025, (For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.).
@article{soton506614,
title = {The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system},
author = {Navamayooran Thavanesan and Mohammad Naiseh and Miguel Terol and Saqib Andrew Rahman and Samuel Luke Hill and Charlotte Parfitt and Zoë S Walters and Sarvapali Ramchurn and Sheraz Markar and Richard Owen and Nick Maynard and Tayyaba Azim and Zehor Belkatir and Elvira Vallejos Perez and Mimi McCord and Tim Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/506614/},
year = {2025},
date = {2025-09-01},
journal = {EClinicalMedicine},
volume = {89},
pages = {103527},
abstract = {ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>},
note = {For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>
3.
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J.; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, vol. 49, no. 11, 2023, (Publisher Copyright: © 2023 The Author(s)).
@article{soton479497b,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J. Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-11-01},
journal = {European Journal of Surgical Oncology},
volume = {49},
number = {11},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
© 2023 The Author(s)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
4.
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub Response Miscellaneous
2023.
@misc{soton481740,
title = {AI large language models inquiry: TASHub Response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
5.
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub response Miscellaneous
2023.
@misc{soton481740b,
title = {AI large language models inquiry: TASHub response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
6.
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, 2023, (Publisher Copyright: copyright 2023 The Author(s)).
@article{soton479497,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-07-01},
journal = {European Journal of Surgical Oncology},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
copyright 2023 The Author(s)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
7.
Krook, Joshua; McAuley, Derek; Anderson, Stuart; Downer, John; Winter, Peter; Ramchurn, Sarvapali D
AI Foundation Models: initial review, CMA Consultation, TAS Hub Response Miscellaneous
2023.
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
publisher = {University of Southampton},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
8.
Krook, Joshua; Downer, John; Winter, Peter; Williams, Jennifer; Ives, Jonathan; Bratu, Roxana; Sheir, Stephanie; Williams, Robin; Anderson, Stuart; Li, Phoebe; Ramamoorthy, Subramanian; Ramchurn, Sarvapali
AI regulation: a pro-innovation approach ? policy proposals: TASHub Response Miscellaneous
2023.
@misc{soton478329,
title = {AI regulation: a pro-innovation approach ? policy proposals: TASHub Response},
author = {Joshua Krook and John Downer and Peter Winter and Jennifer Williams and Jonathan Ives and Roxana Bratu and Stephanie Sheir and Robin Williams and Stuart Anderson and Phoebe Li and Subramanian Ramamoorthy and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478329/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
abstract = {Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence
9.
Yazdanpanah, Vahid; Gerding, Enrico; Stein, Sebastian; Dastani, Mehdi; Jonker, Catholijn M; Norman, Timothy; Ramchurn, Sarvapali
Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities Journal Article
In: AI & Society, 2022.
@article{soton471971,
title = {Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities},
author = {Vahid Yazdanpanah and Enrico Gerding and Sebastian Stein and Mehdi Dastani and Catholijn M Jonker and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/471971/},
year = {2022},
date = {2022-11-01},
journal = {AI & Society},
abstract = {Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.
10.
Soorati, Mohammad Divband; Gerding, Enrico; Marchioni, Enrico; Naumov, Pavel; Norman, Timothy; Ramchurn, Sarvapali; Rastegari, Baharak; Sobey, Adam; Stein, Sebastian; Tarapore, Danesh; Yazdanpanah, Vahid; Zhang, Jie
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems Journal Article
In: AI Communications, 2022.
@article{soton467975,
title = {From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems},
author = {Mohammad Divband Soorati and Enrico Gerding and Enrico Marchioni and Pavel Naumov and Timothy Norman and Sarvapali Ramchurn and Baharak Rastegari and Adam Sobey and Sebastian Stein and Danesh Tarapore and Vahid Yazdanpanah and Jie Zhang},
url = {https://eprints.soton.ac.uk/467975/},
year = {2022},
date = {2022-07-01},
journal = {AI Communications},
abstract = {The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.
11.
Ramchurn, Sarvapali; Middleton, Stuart; McAuley, Derek; Webb, Helena; Hyde, Richard; Lisinska, Justyna
A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee Technical Report
no. 10.18742/pub01-060, 2021.
@techreport{soton451428,
title = {A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee},
author = {Sarvapali Ramchurn and Stuart Middleton and Derek McAuley and Helena Webb and Richard Hyde and Justyna Lisinska},
url = {https://eprints.soton.ac.uk/451428/},
year = {2021},
date = {2021-09-01},
number = {10.18742/pub01-060},
abstract = {This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.
12.
Ramchurn, Sarvapali; Stein, Sebastian; Jennings, Nicholas R
Trustworthy human-AI partnerships Journal Article
In: iScience, vol. 24, no. 8, 2021.
@article{soton450597,
title = {Trustworthy human-AI partnerships},
author = {Sarvapali Ramchurn and Sebastian Stein and Nicholas R Jennings},
url = {https://eprints.soton.ac.uk/450597/},
year = {2021},
date = {2021-08-01},
journal = {iScience},
volume = {24},
number = {8},
abstract = {In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.
13.
Beal, Ryan James; Middleton, Stuart; Norman, Timothy; Ramchurn, Sarvapali
Combining machine learning and human experts to predict match outcomes in football: A baseline model Proceedings Article
In: The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21), 2021.
@inproceedings{soton445607,
title = {Combining machine learning and human experts to predict match outcomes in football: A baseline model},
author = {Ryan James Beal and Stuart Middleton and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445607/},
year = {2021},
date = {2021-02-01},
booktitle = {The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21)},
abstract = {In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
2026
Deshmukh, Jayati; Yazdanpanah, Vahid; Stein, Sebastian; Ramchurn, Gopal
The triad of identity, trust and responsibility in multi-agent systems Proceedings Article
In: 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26), 2026.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Coordination, Ethics, Identity, Multiagent Systems, Norms, Responsibility, Trust
@inproceedings{soton509930,
title = {The triad of identity, trust and responsibility in multi-agent systems},
author = {Jayati Deshmukh and Vahid Yazdanpanah and Sebastian Stein and Gopal Ramchurn},
url = {https://eprints.soton.ac.uk/509930/},
year = {2026},
date = {2026-05-01},
booktitle = {25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26)},
abstract = {The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.},
keywords = {Artificial Intelligence, Coordination, Ethics, Identity, Multiagent Systems, Norms, Responsibility, Trust},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.
2025
Thavanesan, Navamayooran; Naiseh, Mohammad; Terol, Miguel; Rahman, Saqib Andrew; Hill, Samuel Luke; Parfitt, Charlotte; Walters, Zoë S; Ramchurn, Sarvapali; Markar, Sheraz; Owen, Richard; Maynard, Nick; Azim, Tayyaba; Belkatir, Zehor; Perez, Elvira Vallejos; McCord, Mimi; Underwood, Tim; Vigneswaran, Ganesh
The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system Journal Article
In: EClinicalMedicine, vol. 89, pp. 103527, 2025, (For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Decision support tool, machine learning, MDT, Multidisciplinary teams, Oesophageal cancer
@article{soton506614,
title = {The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system},
author = {Navamayooran Thavanesan and Mohammad Naiseh and Miguel Terol and Saqib Andrew Rahman and Samuel Luke Hill and Charlotte Parfitt and Zoë S Walters and Sarvapali Ramchurn and Sheraz Markar and Richard Owen and Nick Maynard and Tayyaba Azim and Zehor Belkatir and Elvira Vallejos Perez and Mimi McCord and Tim Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/506614/},
year = {2025},
date = {2025-09-01},
journal = {EClinicalMedicine},
volume = {89},
pages = {103527},
abstract = {ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>},
note = {For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.},
keywords = {Artificial Intelligence, Decision support tool, machine learning, MDT, Multidisciplinary teams, Oesophageal cancer},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>
2023
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J.; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, vol. 49, no. 11, 2023, (Publisher Copyright: © 2023 The Author(s)).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team
@article{soton479497b,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J. Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-11-01},
journal = {European Journal of Surgical Oncology},
volume = {49},
number = {11},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
© 2023 The Author(s)},
keywords = {Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub Response Miscellaneous
2023.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy
@misc{soton481740,
title = {AI large language models inquiry: TASHub Response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub response Miscellaneous
2023.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy
@misc{soton481740b,
title = {AI large language models inquiry: TASHub response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {Artificial Intelligence, chatgpt, european law, generative ai, Large Language Models, law and technology, technology policy},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, 2023, (Publisher Copyright: copyright 2023 The Author(s)).
Abstract | Links | BibTeX | Tags: Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team
@article{soton479497,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-07-01},
journal = {European Journal of Surgical Oncology},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
copyright 2023 The Author(s)},
keywords = {Artificial Intelligence, machine learning, Oesophageal cancer multidisciplinary team},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
Krook, Joshua; McAuley, Derek; Anderson, Stuart; Downer, John; Winter, Peter; Ramchurn, Sarvapali D
AI Foundation Models: initial review, CMA Consultation, TAS Hub Response Miscellaneous
2023.
Links | BibTeX | Tags: Artificial Intelligence, Competition policy, featured_publication, Foundation Models, Large Language Models, markets
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
publisher = {University of Southampton},
keywords = {Artificial Intelligence, Competition policy, featured_publication, Foundation Models, Large Language Models, markets},
pubstate = {published},
tppubtype = {misc}
}
Krook, Joshua; Downer, John; Winter, Peter; Williams, Jennifer; Ives, Jonathan; Bratu, Roxana; Sheir, Stephanie; Williams, Robin; Anderson, Stuart; Li, Phoebe; Ramamoorthy, Subramanian; Ramchurn, Sarvapali
AI regulation: a pro-innovation approach ? policy proposals: TASHub Response Miscellaneous
2023.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Consultation, innovation, Regulation, Trustworthy Autonomous Systems
@misc{soton478329,
title = {AI regulation: a pro-innovation approach ? policy proposals: TASHub Response},
author = {Joshua Krook and John Downer and Peter Winter and Jennifer Williams and Jonathan Ives and Roxana Bratu and Stephanie Sheir and Robin Williams and Stuart Anderson and Phoebe Li and Subramanian Ramamoorthy and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478329/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
abstract = {Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence},
keywords = {Artificial Intelligence, Consultation, innovation, Regulation, Trustworthy Autonomous Systems},
pubstate = {published},
tppubtype = {misc}
}
Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence
2022
Yazdanpanah, Vahid; Gerding, Enrico; Stein, Sebastian; Dastani, Mehdi; Jonker, Catholijn M; Norman, Timothy; Ramchurn, Sarvapali
Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities Journal Article
In: AI & Society, 2022.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Citizen-Centric AI Systems, human-agent collectives, Human-Centred AI, Multiagent Responsibility Reasoning, Multiagent Systems, Trustworthy Autonomous Systems
@article{soton471971,
title = {Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities},
author = {Vahid Yazdanpanah and Enrico Gerding and Sebastian Stein and Mehdi Dastani and Catholijn M Jonker and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/471971/},
year = {2022},
date = {2022-11-01},
journal = {AI & Society},
abstract = {Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.},
keywords = {Artificial Intelligence, Citizen-Centric AI Systems, human-agent collectives, Human-Centred AI, Multiagent Responsibility Reasoning, Multiagent Systems, Trustworthy Autonomous Systems},
pubstate = {published},
tppubtype = {article}
}
Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.
Soorati, Mohammad Divband; Gerding, Enrico; Marchioni, Enrico; Naumov, Pavel; Norman, Timothy; Ramchurn, Sarvapali; Rastegari, Baharak; Sobey, Adam; Stein, Sebastian; Tarapore, Danesh; Yazdanpanah, Vahid; Zhang, Jie
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems Journal Article
In: AI Communications, 2022.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Distributed Artificial Intelligence, Intelligent Agents, Multiagent Systems, Trustworthy Autonomous Systems
@article{soton467975,
title = {From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems},
author = {Mohammad Divband Soorati and Enrico Gerding and Enrico Marchioni and Pavel Naumov and Timothy Norman and Sarvapali Ramchurn and Baharak Rastegari and Adam Sobey and Sebastian Stein and Danesh Tarapore and Vahid Yazdanpanah and Jie Zhang},
url = {https://eprints.soton.ac.uk/467975/},
year = {2022},
date = {2022-07-01},
journal = {AI Communications},
abstract = {The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.},
keywords = {Artificial Intelligence, Distributed Artificial Intelligence, Intelligent Agents, Multiagent Systems, Trustworthy Autonomous Systems},
pubstate = {published},
tppubtype = {article}
}
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.
2021
Ramchurn, Sarvapali; Middleton, Stuart; McAuley, Derek; Webb, Helena; Hyde, Richard; Lisinska, Justyna
A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee Technical Report
no. 10.18742/pub01-060, 2021.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Online Harms
@techreport{soton451428,
title = {A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee},
author = {Sarvapali Ramchurn and Stuart Middleton and Derek McAuley and Helena Webb and Richard Hyde and Justyna Lisinska},
url = {https://eprints.soton.ac.uk/451428/},
year = {2021},
date = {2021-09-01},
number = {10.18742/pub01-060},
abstract = {This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.},
keywords = {Artificial Intelligence, Online Harms},
pubstate = {published},
tppubtype = {techreport}
}
This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.
Ramchurn, Sarvapali; Stein, Sebastian; Jennings, Nicholas R
Trustworthy human-AI partnerships Journal Article
In: iScience, vol. 24, no. 8, 2021.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Human-Computer Interaction, Sociology
@article{soton450597,
title = {Trustworthy human-AI partnerships},
author = {Sarvapali Ramchurn and Sebastian Stein and Nicholas R Jennings},
url = {https://eprints.soton.ac.uk/450597/},
year = {2021},
date = {2021-08-01},
journal = {iScience},
volume = {24},
number = {8},
abstract = {In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.},
keywords = {Artificial Intelligence, Human-Computer Interaction, Sociology},
pubstate = {published},
tppubtype = {article}
}
In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.
Beal, Ryan James; Middleton, Stuart; Norman, Timothy; Ramchurn, Sarvapali
Combining machine learning and human experts to predict match outcomes in football: A baseline model Proceedings Article
In: The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21), 2021.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Natural Language Processing
@inproceedings{soton445607,
title = {Combining machine learning and human experts to predict match outcomes in football: A baseline model},
author = {Ryan James Beal and Stuart Middleton and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445607/},
year = {2021},
date = {2021-02-01},
booktitle = {The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21)},
abstract = {In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.},
keywords = {Artificial Intelligence, Natural Language Processing},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
1.
Deshmukh, Jayati; Yazdanpanah, Vahid; Stein, Sebastian; Ramchurn, Gopal
The triad of identity, trust and responsibility in multi-agent systems Proceedings Article
In: 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26), 2026.
@inproceedings{soton509930,
title = {The triad of identity, trust and responsibility in multi-agent systems},
author = {Jayati Deshmukh and Vahid Yazdanpanah and Sebastian Stein and Gopal Ramchurn},
url = {https://eprints.soton.ac.uk/509930/},
year = {2026},
date = {2026-05-01},
booktitle = {25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26)},
abstract = {The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.
2.
Thavanesan, Navamayooran; Naiseh, Mohammad; Terol, Miguel; Rahman, Saqib Andrew; Hill, Samuel Luke; Parfitt, Charlotte; Walters, Zoë S; Ramchurn, Sarvapali; Markar, Sheraz; Owen, Richard; Maynard, Nick; Azim, Tayyaba; Belkatir, Zehor; Perez, Elvira Vallejos; McCord, Mimi; Underwood, Tim; Vigneswaran, Ganesh
The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system Journal Article
In: EClinicalMedicine, vol. 89, pp. 103527, 2025, (For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.).
@article{soton506614,
title = {The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system},
author = {Navamayooran Thavanesan and Mohammad Naiseh and Miguel Terol and Saqib Andrew Rahman and Samuel Luke Hill and Charlotte Parfitt and Zoë S Walters and Sarvapali Ramchurn and Sheraz Markar and Richard Owen and Nick Maynard and Tayyaba Azim and Zehor Belkatir and Elvira Vallejos Perez and Mimi McCord and Tim Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/506614/},
year = {2025},
date = {2025-09-01},
journal = {EClinicalMedicine},
volume = {89},
pages = {103527},
abstract = {ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>},
note = {For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>
3.
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J.; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, vol. 49, no. 11, 2023, (Publisher Copyright: © 2023 The Author(s)).
@article{soton479497b,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J. Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-11-01},
journal = {European Journal of Surgical Oncology},
volume = {49},
number = {11},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
© 2023 The Author(s)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
4.
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub Response Miscellaneous
2023.
@misc{soton481740,
title = {AI large language models inquiry: TASHub Response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
5.
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub response Miscellaneous
2023.
@misc{soton481740b,
title = {AI large language models inquiry: TASHub response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
6.
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, 2023, (Publisher Copyright: copyright 2023 The Author(s)).
@article{soton479497,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-07-01},
journal = {European Journal of Surgical Oncology},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
copyright 2023 The Author(s)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
7.
Krook, Joshua; McAuley, Derek; Anderson, Stuart; Downer, John; Winter, Peter; Ramchurn, Sarvapali D
AI Foundation Models: initial review, CMA Consultation, TAS Hub Response Miscellaneous
2023.
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
publisher = {University of Southampton},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
8.
Krook, Joshua; Downer, John; Winter, Peter; Williams, Jennifer; Ives, Jonathan; Bratu, Roxana; Sheir, Stephanie; Williams, Robin; Anderson, Stuart; Li, Phoebe; Ramamoorthy, Subramanian; Ramchurn, Sarvapali
AI regulation: a pro-innovation approach ? policy proposals: TASHub Response Miscellaneous
2023.
@misc{soton478329,
title = {AI regulation: a pro-innovation approach ? policy proposals: TASHub Response},
author = {Joshua Krook and John Downer and Peter Winter and Jennifer Williams and Jonathan Ives and Roxana Bratu and Stephanie Sheir and Robin Williams and Stuart Anderson and Phoebe Li and Subramanian Ramamoorthy and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478329/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
abstract = {Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence
9.
Yazdanpanah, Vahid; Gerding, Enrico; Stein, Sebastian; Dastani, Mehdi; Jonker, Catholijn M; Norman, Timothy; Ramchurn, Sarvapali
Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities Journal Article
In: AI & Society, 2022.
@article{soton471971,
title = {Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities},
author = {Vahid Yazdanpanah and Enrico Gerding and Sebastian Stein and Mehdi Dastani and Catholijn M Jonker and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/471971/},
year = {2022},
date = {2022-11-01},
journal = {AI & Society},
abstract = {Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.
10.
Soorati, Mohammad Divband; Gerding, Enrico; Marchioni, Enrico; Naumov, Pavel; Norman, Timothy; Ramchurn, Sarvapali; Rastegari, Baharak; Sobey, Adam; Stein, Sebastian; Tarapore, Danesh; Yazdanpanah, Vahid; Zhang, Jie
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems Journal Article
In: AI Communications, 2022.
@article{soton467975,
title = {From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems},
author = {Mohammad Divband Soorati and Enrico Gerding and Enrico Marchioni and Pavel Naumov and Timothy Norman and Sarvapali Ramchurn and Baharak Rastegari and Adam Sobey and Sebastian Stein and Danesh Tarapore and Vahid Yazdanpanah and Jie Zhang},
url = {https://eprints.soton.ac.uk/467975/},
year = {2022},
date = {2022-07-01},
journal = {AI Communications},
abstract = {The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.
11.
Ramchurn, Sarvapali; Middleton, Stuart; McAuley, Derek; Webb, Helena; Hyde, Richard; Lisinska, Justyna
A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee Technical Report
no. 10.18742/pub01-060, 2021.
@techreport{soton451428,
title = {A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee},
author = {Sarvapali Ramchurn and Stuart Middleton and Derek McAuley and Helena Webb and Richard Hyde and Justyna Lisinska},
url = {https://eprints.soton.ac.uk/451428/},
year = {2021},
date = {2021-09-01},
number = {10.18742/pub01-060},
abstract = {This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.
12.
Ramchurn, Sarvapali; Stein, Sebastian; Jennings, Nicholas R
Trustworthy human-AI partnerships Journal Article
In: iScience, vol. 24, no. 8, 2021.
@article{soton450597,
title = {Trustworthy human-AI partnerships},
author = {Sarvapali Ramchurn and Sebastian Stein and Nicholas R Jennings},
url = {https://eprints.soton.ac.uk/450597/},
year = {2021},
date = {2021-08-01},
journal = {iScience},
volume = {24},
number = {8},
abstract = {In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.
13.
Beal, Ryan James; Middleton, Stuart; Norman, Timothy; Ramchurn, Sarvapali
Combining machine learning and human experts to predict match outcomes in football: A baseline model Proceedings Article
In: The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21), 2021.
@inproceedings{soton445607,
title = {Combining machine learning and human experts to predict match outcomes in football: A baseline model},
author = {Ryan James Beal and Stuart Middleton and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445607/},
year = {2021},
date = {2021-02-01},
booktitle = {The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21)},
abstract = {In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
Selected Publications
Multi-agent signal-less intersection management with dynamic platoon formation
No data available.
https://eprints.soton.ac.uk/478647/
@inproceedings{soton478647,
title = {Multi-agent signal-less intersection management with dynamic platoon formation},
author = {Phuriwat Worrawichaipat and Enrico Gerding and Ioannis Kaparias and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478647/},
year = {2023},
date = {2023-05-01},
booktitle = {22nd International Conference on Autonomous Agents and Multiagent Systems (29/05/23 - 02/06/23)},
pages = {1542--1550},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
title = {Multi-agent signal-less intersection management with dynamic platoon formation},
author = {Phuriwat Worrawichaipat and Enrico Gerding and Ioannis Kaparias and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478647/},
year = {2023},
date = {2023-05-01},
booktitle = {22nd International Conference on Autonomous Agents and Multiagent Systems (29/05/23 - 02/06/23)},
pages = {1542--1550},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
AI Foundation Models: initial review, CMA Consultation, TAS Hub Response
No data available.
https://eprints.soton.ac.uk/477553/
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
The effect of data visualisation quality and task density on human-swarm interaction
No data available.
https://eprints.soton.ac.uk/479970/
@inproceedings{soton479970,
title = {The effect of data visualisation quality and task density on human-swarm interaction},
author = {Ayodeji Abioye and Mohammad Naiseh and William Hunt and Jediah R Clark and Sarvapali D Ramchurn and Mohammad Soorati},
url = {https://eprints.soton.ac.uk/479970/},
year = {2023},
date = {2023-06-01},
booktitle = {Proceedings of the 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},
publisher = {IEEE},
abstract = {Despite the advantages of having robot swarms, human supervision is required for real-world applications. The performance of the human-swarm system depends on several factors including the data availability for the human operators. In this paper, we study the human factors aspect of the human-swarm interaction and investigate how having access to high-quality data can affect the performance of the human-swarm system - the number of tasks completed and the human trust level in operation. We designed an experiment where a human operator is tasked to operate a swarm to identify casualties in an area within a given time period. One group of operators had the option to request high-quality pictures while the other group had to base their decision on the available low-quality images. We performed a user study with 120 participants and recorded their success rate (directly logged via the simulation platform) as well as their workload and trust level (measured through a questionnaire after completing a human-swarm scenario). The findings from our study indicated that the group granted access to high-quality data exhibited an increased workload and placed greater trust in the swarm, thus confirming our initial hypothesis. However, we also found that the number of accurately identified casualties did not significantly vary between the two groups, suggesting that data quality had no impact on the successful completion of tasks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
title = {The effect of data visualisation quality and task density on human-swarm interaction},
author = {Ayodeji Abioye and Mohammad Naiseh and William Hunt and Jediah R Clark and Sarvapali D Ramchurn and Mohammad Soorati},
url = {https://eprints.soton.ac.uk/479970/},
year = {2023},
date = {2023-06-01},
booktitle = {Proceedings of the 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)},
publisher = {IEEE},
abstract = {Despite the advantages of having robot swarms, human supervision is required for real-world applications. The performance of the human-swarm system depends on several factors including the data availability for the human operators. In this paper, we study the human factors aspect of the human-swarm interaction and investigate how having access to high-quality data can affect the performance of the human-swarm system - the number of tasks completed and the human trust level in operation. We designed an experiment where a human operator is tasked to operate a swarm to identify casualties in an area within a given time period. One group of operators had the option to request high-quality pictures while the other group had to base their decision on the available low-quality images. We performed a user study with 120 participants and recorded their success rate (directly logged via the simulation platform) as well as their workload and trust level (measured through a questionnaire after completing a human-swarm scenario). The findings from our study indicated that the group granted access to high-quality data exhibited an increased workload and placed greater trust in the swarm, thus confirming our initial hypothesis. However, we also found that the number of accurately identified casualties did not significantly vary between the two groups, suggesting that data quality had no impact on the successful completion of tasks.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Demonstrating performance benefits of human-swarm teaming
Autonomous swarms of robots can bring robustness, scalability and adaptability to safety-critical tasks such as search and rescue but their application is still very limited. Using semi-autonomous swarms with human control can bring robot swarms to real-world applications. Human operators can define goals for the swarm, monitor their performance and interfere with, or overrule, the decisions and behaviour. We present the "Human And Robot Interactive Swarm'' simulator (HARIS) that allows multi-user interaction with a robot swarm and facilitates qualitative and quantitative user studies through simulation of robot swarms completing tasks, from package delivery to search and rescue, with varying levels of human control. In this demonstration, we showcase the simulator by using it to study the performance gain offered by maintaining a "human-in-the-loop'' over a fully autonomous system as an example. This is illustrated in the context of search and rescue, with an autonomous allocation of resources to those in need.
https://eprints.soton.ac.uk/479903/
@inproceedings{soton479903,
title = {Demonstrating performance benefits of human-swarm teaming},
author = {William Hunt and Jack Ryan and Ayodeji O Abioye and Sarvapali D Ramchurn and Mohammad D Soorati},
url = {https://eprints.soton.ac.uk/479903/},
year = {2023},
date = {2023-05-01},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems},
pages = {3062--3064},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)},
abstract = {Autonomous swarms of robots can bring robustness, scalability and adaptability to safety-critical tasks such as search and rescue but their application is still very limited. Using semi-autonomous swarms with human control can bring robot swarms to real-world applications. Human operators can define goals for the swarm, monitor their performance and interfere with, or overrule, the decisions and behaviour. We present the "Human And Robot Interactive Swarm'' simulator (HARIS) that allows multi-user interaction with a robot swarm and facilitates qualitative and quantitative user studies through simulation of robot swarms completing tasks, from package delivery to search and rescue, with varying levels of human control. In this demonstration, we showcase the simulator by using it to study the performance gain offered by maintaining a "human-in-the-loop'' over a fully autonomous system as an example. This is illustrated in the context of search and rescue, with an autonomous allocation of resources to those in need.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
title = {Demonstrating performance benefits of human-swarm teaming},
author = {William Hunt and Jack Ryan and Ayodeji O Abioye and Sarvapali D Ramchurn and Mohammad D Soorati},
url = {https://eprints.soton.ac.uk/479903/},
year = {2023},
date = {2023-05-01},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems},
pages = {3062--3064},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)},
abstract = {Autonomous swarms of robots can bring robustness, scalability and adaptability to safety-critical tasks such as search and rescue but their application is still very limited. Using semi-autonomous swarms with human control can bring robot swarms to real-world applications. Human operators can define goals for the swarm, monitor their performance and interfere with, or overrule, the decisions and behaviour. We present the "Human And Robot Interactive Swarm'' simulator (HARIS) that allows multi-user interaction with a robot swarm and facilitates qualitative and quantitative user studies through simulation of robot swarms completing tasks, from package delivery to search and rescue, with varying levels of human control. In this demonstration, we showcase the simulator by using it to study the performance gain offered by maintaining a "human-in-the-loop'' over a fully autonomous system as an example. This is illustrated in the context of search and rescue, with an autonomous allocation of resources to those in need.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2026
Deshmukh, Jayati; Yazdanpanah, Vahid; Stein, Sebastian; Ramchurn, Gopal
The triad of identity, trust and responsibility in multi-agent systems Proceedings Article
In: 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26), 2026.
@inproceedings{soton509930,
title = {The triad of identity, trust and responsibility in multi-agent systems},
author = {Jayati Deshmukh and Vahid Yazdanpanah and Sebastian Stein and Gopal Ramchurn},
url = {https://eprints.soton.ac.uk/509930/},
year = {2026},
date = {2026-05-01},
booktitle = {25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026) (25/05/26 - 29/05/26)},
abstract = {The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The design of autonomous AI agents that behave responsibly and foster trust in open multi-agent systems remains a fundamental challenge. Traditional game-theoretical approaches largely assume self-interested behaviour, yet real-world collaborations among humans often rely on prosocial considerations that extend beyond individual utility. To address this, for the first time in this paper, we investigate the triad of identity, responsibility, and trust as core elements shaping responsible multi-agent behaviour. We propose a novel agent model, building on the notion of Computational Transcendence, which equips agents with an elastic sense of identity, enabling them to incorporate the welfare of others into their decision-making. Our framework integrates subjective (identity-based) and objective (experience-based and reputation-based) components of trust. Using Iterated Prisoner?s Dilemma (IPD) simulations on different network structures, we analyse how varying levels of identity and trust affect responsible behaviour. Results demonstrate that the interplay of these three concepts can promote emergent responsibility, mitigate exploitation, and sustain long-term cooperation in dynamic multi-agent environments. We argue that this triadic perspective provides a principled foundation for designing trustworthy, responsible, and identity/value aware agents with implications for future human?AI collaboration.
2025
Thavanesan, Navamayooran; Naiseh, Mohammad; Terol, Miguel; Rahman, Saqib Andrew; Hill, Samuel Luke; Parfitt, Charlotte; Walters, Zoë S; Ramchurn, Sarvapali; Markar, Sheraz; Owen, Richard; Maynard, Nick; Azim, Tayyaba; Belkatir, Zehor; Perez, Elvira Vallejos; McCord, Mimi; Underwood, Tim; Vigneswaran, Ganesh
The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system Journal Article
In: EClinicalMedicine, vol. 89, pp. 103527, 2025, (For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.).
@article{soton506614,
title = {The oesophageal cancer multi-disciplinary tool: a co-designed, externally validated, machine learning clinical decision support system},
author = {Navamayooran Thavanesan and Mohammad Naiseh and Miguel Terol and Saqib Andrew Rahman and Samuel Luke Hill and Charlotte Parfitt and Zoë S Walters and Sarvapali Ramchurn and Sheraz Markar and Richard Owen and Nick Maynard and Tayyaba Azim and Zehor Belkatir and Elvira Vallejos Perez and Mimi McCord and Tim Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/506614/},
year = {2025},
date = {2025-09-01},
journal = {EClinicalMedicine},
volume = {89},
pages = {103527},
abstract = {ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>},
note = {For the purposes of open access, the authors have applied a Creative Commons attribution license (CC-BY) to any Author Accepted Manuscript version arising from this submission.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>BACKGROUND: The oesophageal cancer (OC) multi-disciplinary team (MDT) operates under significant pressures, handling complex decision-making. Machine learning (ML) can learn complex decision-making paradigms to improve efficiency, consistency, and cost if trained and deployed responsibly. We present an externally validated ML-based clinical decision support system (CDSS) designed to predict OC MDT treatment decisions and prognosticate palliative scenarios, co-designed using Responsible Research and Innovation (RRI) principles.ensuremath</pensuremath>ensuremath<pensuremath>METHODS: Clinicopathological data collected from 1931 patients between 4th September 2009, and 8th November 2022 were used to test and validate models trained through four ML algorithms to predict curative and palliative treatment pathways along with palliative prognosis. 953 OC cases treated at University Hospitals Southampton (UHS) were used to train ML models which were externally validated on 978 OC cases from Oxford University Hospitals (OUH). Model performance was evaluated using Area Under Curve (AUC) for treatment classifiers and calibration curves for survival models. A parallel RRI program at the University of Southampton (United Kingdom) combining clinician interviews and inter-disciplinary workshops was conducted between 16.3.23 and 23.5.24. The RRI program comprised a group of 17 domain experts comprising programmers, computer scientists, clinicians and patient representatives to allow end-users to contribute towards the co-design of the CDSS user interface.ensuremath</pensuremath>ensuremath<pensuremath>FINDINGS: Cohorts differed in baseline characteristics, with the external cohort (OUH) being younger, having better performance status, and a higher prevalence of pulmonary and vascular disease. Despite these differences, on internal validation (UHS cohort) mean AUCs for the primary treatment model were: MLR 0.905 $±$ 0.048, XGB 0.909 $±$ 0.044 and RF 0.883 $±$ 0.059 (k = 5 cross-validation) and MLR 0.866 (95% CI 0.866-0.867), XGB 0.863 (0.862-0.864), RF 0.863 (0.867-0.868) on bootstrapped resampling. For the palliative classifier, mean AUCs were: MLR 0.805 $±$ 0.096, XGB 0.815 $±$ 0.081 and RF 0.793 $±$ 0.083 (k = 5 cross-validation) and MLR 0.736 (95% CI 0.734-0.737), XGB 0.799 (0.798-0.800), RF 0.781 (0.778-0.782) on bootstrapped resampling. On external validation (OUH cohort), AUCs were MLR 0.894, XGB 0.887 and RF 0.891 for the primary treatment model and MLR 0.711, XGB 0.742 and RF 0.730 for the palliative treatment classifier. Predicted survival probability from the palliative survival model was well calibrated over the first 12 months post-diagnosis in both cohorts. The RRI program provided a collaborative environment leading to valuable modifications to the CDSS including prediction explanations, visual aids for survival and integrated education for users producing a user-friendly and quick to use tool.ensuremath</pensuremath>ensuremath<pensuremath>INTERPRETATION: We present a novel, responsibly developed, externally validated AI CDSS trained to predict oesophageal cancer MDT decisions. It represents the foundations of a transformative application of ML, personalised, consistent and efficient MDT decision-support within OC which aligns to RRI principles.ensuremath</pensuremath>ensuremath<pensuremath>FUNDING: Doctoral Studentship for NT (Institute for Life Sciences (University of Southampton) & University Hospital Southampton), UKRI TAS Pump-Priming Grant (TAS_PP_00167).ensuremath</pensuremath>
2023
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J.; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, vol. 49, no. 11, 2023, (Publisher Copyright: © 2023 The Author(s)).
@article{soton479497b,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J. Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-11-01},
journal = {European Journal of Surgical Oncology},
volume = {49},
number = {11},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
© 2023 The Author(s)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $±$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$±$0.045] vs 0.757 [$±$0.068], 0.740 [$±$0.042], and 0.709 [$±$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub Response Miscellaneous
2023.
@misc{soton481740,
title = {AI large language models inquiry: TASHub Response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
Krook, Joshua; Williams, Jennifer; Seabrooke, Tina; Schneiders, Eike; Blockx, Jan; Middleton, Stuart E; Ramchurn, Sarvapali
AI large language models inquiry: TASHub response Miscellaneous
2023.
@misc{soton481740b,
title = {AI large language models inquiry: TASHub response},
author = {Joshua Krook and Jennifer Williams and Tina Seabrooke and Eike Schneiders and Jan Blockx and Stuart E Middleton and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/481740/},
year = {2023},
date = {2023-08-01},
publisher = {University of Southampton},
abstract = {Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Policy submission to the Consultation by Communications and Digital Committee, House of Lords, AI Large Language Models Inquiry.ensuremath<br/ensuremath>
Thavanesan, Navamayooran; Bodala, Indu; Walters, Zoe; Ramchurn, Sarvapali; Underwood, Timothy J; Vigneswaran, Ganesh
Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer Journal Article
In: European Journal of Surgical Oncology, 2023, (Publisher Copyright: copyright 2023 The Author(s)).
@article{soton479497,
title = {Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer},
author = {Navamayooran Thavanesan and Indu Bodala and Zoe Walters and Sarvapali Ramchurn and Timothy J Underwood and Ganesh Vigneswaran},
url = {https://eprints.soton.ac.uk/479497/},
year = {2023},
date = {2023-07-01},
journal = {European Journal of Surgical Oncology},
abstract = {ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>},
note = {Publisher Copyright:
copyright 2023 The Author(s)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
ensuremath<pensuremath>Background: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. Methods: Retrospective complete-case analysis of oesophagectomy patients $pm$ neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. Results: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32?83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [$pm$0.045] vs 0.757 [$pm$0.068], 0.740 [$pm$0.042], and 0.709 [$pm$0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). Conclusions: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.ensuremath</pensuremath>
Krook, Joshua; McAuley, Derek; Anderson, Stuart; Downer, John; Winter, Peter; Ramchurn, Sarvapali D
AI Foundation Models: initial review, CMA Consultation, TAS Hub Response Miscellaneous
2023.
@misc{soton477553,
title = {AI Foundation Models: initial review, CMA Consultation, TAS Hub Response},
author = {Joshua Krook and Derek McAuley and Stuart Anderson and John Downer and Peter Winter and Sarvapali D Ramchurn},
url = {https://eprints.soton.ac.uk/477553/},
year = {2023},
date = {2023-06-01},
urldate = {2023-06-01},
publisher = {University of Southampton},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Krook, Joshua; Downer, John; Winter, Peter; Williams, Jennifer; Ives, Jonathan; Bratu, Roxana; Sheir, Stephanie; Williams, Robin; Anderson, Stuart; Li, Phoebe; Ramamoorthy, Subramanian; Ramchurn, Sarvapali
AI regulation: a pro-innovation approach ? policy proposals: TASHub Response Miscellaneous
2023.
@misc{soton478329,
title = {AI regulation: a pro-innovation approach ? policy proposals: TASHub Response},
author = {Joshua Krook and John Downer and Peter Winter and Jennifer Williams and Jonathan Ives and Roxana Bratu and Stephanie Sheir and Robin Williams and Stuart Anderson and Phoebe Li and Subramanian Ramamoorthy and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/478329/},
year = {2023},
date = {2023-06-01},
publisher = {University of Southampton},
abstract = {Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Response to open consultation from: Department for Science, Innovation and Technologyensuremath<br/ensuremath>and Office for Artificial Intelligence
2022
Yazdanpanah, Vahid; Gerding, Enrico; Stein, Sebastian; Dastani, Mehdi; Jonker, Catholijn M; Norman, Timothy; Ramchurn, Sarvapali
Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities Journal Article
In: AI & Society, 2022.
@article{soton471971,
title = {Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities},
author = {Vahid Yazdanpanah and Enrico Gerding and Sebastian Stein and Mehdi Dastani and Catholijn M Jonker and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/471971/},
year = {2022},
date = {2022-11-01},
journal = {AI & Society},
abstract = {Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ensuring the trustworthiness of autonomous systems and artificial intelligenceensuremath<br/ensuremath>is an important interdisciplinary endeavour. In this position paper, we argue thatensuremath<br/ensuremath>this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals? responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.
Soorati, Mohammad Divband; Gerding, Enrico; Marchioni, Enrico; Naumov, Pavel; Norman, Timothy; Ramchurn, Sarvapali; Rastegari, Baharak; Sobey, Adam; Stein, Sebastian; Tarapore, Danesh; Yazdanpanah, Vahid; Zhang, Jie
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems Journal Article
In: AI Communications, 2022.
@article{soton467975,
title = {From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems},
author = {Mohammad Divband Soorati and Enrico Gerding and Enrico Marchioni and Pavel Naumov and Timothy Norman and Sarvapali Ramchurn and Baharak Rastegari and Adam Sobey and Sebastian Stein and Danesh Tarapore and Vahid Yazdanpanah and Jie Zhang},
url = {https://eprints.soton.ac.uk/467975/},
year = {2022},
date = {2022-07-01},
journal = {AI Communications},
abstract = {The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.
2021
Ramchurn, Sarvapali; Middleton, Stuart; McAuley, Derek; Webb, Helena; Hyde, Richard; Lisinska, Justyna
A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee Technical Report
no. 10.18742/pub01-060, 2021.
@techreport{soton451428,
title = {A Response to Draft Online Safety Bill: A call for evidence from the Joint Committee},
author = {Sarvapali Ramchurn and Stuart Middleton and Derek McAuley and Helena Webb and Richard Hyde and Justyna Lisinska},
url = {https://eprints.soton.ac.uk/451428/},
year = {2021},
date = {2021-09-01},
number = {10.18742/pub01-060},
abstract = {This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a new regulatory framework to tackle harmful content online.
Ramchurn, Sarvapali; Stein, Sebastian; Jennings, Nicholas R
Trustworthy human-AI partnerships Journal Article
In: iScience, vol. 24, no. 8, 2021.
@article{soton450597,
title = {Trustworthy human-AI partnerships},
author = {Sarvapali Ramchurn and Sebastian Stein and Nicholas R Jennings},
url = {https://eprints.soton.ac.uk/450597/},
year = {2021},
date = {2021-08-01},
journal = {iScience},
volume = {24},
number = {8},
abstract = {In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we foreground some of the key research challenges that arise in the design of trustworthy human-AI partnerships. In particular, we focus on the challenges in designing human-AI partnerships that need to be addressed to help humans and organisations trust their machine counterparts individually or as a collective (e.g., as robot teams or groups of software agents). We also aim to identify the risks associated with human-AI partnerships and therefore determine the associated measures to mitigate these risks. By so doing, we will trigger new avenues of research that will address the key barriers to the adoption of AI-based systems more widely in our daily lives and in industry.
Beal, Ryan James; Middleton, Stuart; Norman, Timothy; Ramchurn, Sarvapali
Combining machine learning and human experts to predict match outcomes in football: A baseline model Proceedings Article
In: The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21), 2021.
@inproceedings{soton445607,
title = {Combining machine learning and human experts to predict match outcomes in football: A baseline model},
author = {Ryan James Beal and Stuart Middleton and Timothy Norman and Sarvapali Ramchurn},
url = {https://eprints.soton.ac.uk/445607/},
year = {2021},
date = {2021-02-01},
booktitle = {The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (02/02/21 - 09/02/21)},
abstract = {In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.