Short biography

Mengwei studied Mathematics for his undergraduate. After the undergraduate, Mengwei pursued a PhD degree in autonomous agents, planning, and multi-criteria decision making, supervised by Professor Weiru Liu at University of Bristol. After the PhD, Mengwei joined the Formal Analysis, Theory and Algorithms Group as a Research Associate working on trustworthy autonomous agents with Professor Dame Muffy Calder, Dr. Michele Sevegnani, and Dr Blair Archibald at the University of Glasgow. After it, Mengwei was a member of Autonomy and Verification Group as Research Fellow from Jan 2023 to August 2023 under the supervision of Dr. Louise Dennis, focusing on safeguarding data privacy through trustworthy autonomous agents, at the University of Manchester. Currently, Mengwei is a lecturer at Group of Advanced Model-Based Engineering and Reasoning (AMBER) at the School of Computing at the University of Newcasle.

Topics of Interest

- Autonomous agent systems

- Automated planning

- Formal methods

Publication

* denotes the principal or corresponding author.

Recent works submitted for publication

• Run-time Quantitative Operational Monitoring for Autonomous Systems
  Marie Farrell, Angelo Ferrando and Mengwei Xu

Published works

[14]	Safeguard Privacy for Minimal Data Collection with Trustworthy Autonomous Agents. Mengwei Xu*, Louise Dennis, and Mustafa Mustafa. In 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), To appear. (acceptance rate 25%)
[13]	CAN-verify: Verification Tool for BDI Agents. [Artifacts Available] [Artifacts Evaluated] Mengwei Xu*, Thibault Rivoalen, Blair Archibald, and Michele Sevegnani. In 18th International Conference on integrated Formal Methods (IFM), pages 364-373, 2023. [ bib | DOI | pdf | slides  ]
[12]	Quantitative Modelling and Analysis of BDI Agents. [SEFM 2021 Invited Paper] Blair Archibald, Muffy Calder, Michele Sevegnani, and Mengwei Xu*. In Software and Systems Modeling, 2023. [ bib | DOI | pdf ]
[11]	Uncertain Machine Ethical Decisions Using Hypothetical Retrospection. Simon Kolker, Louise Dennis, Ramon Fraga Pereira, and Mengwei Xu. In 27th International Workshop on Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE), pages 364-373, 2023. [ bib | DOI | pdf ]
[10]	Successful Swarms: Operator Situational Awareness via Runtime Formal Methods. Yue Gu, William Hunt, Blair Archibald, Mengwei Xu, Michele Sevegnani and Mohammad D. Soorati. In IEEE 32nd International Conference on Robot and Human Interactive Communication (IEEE RO-MAN), pages 541-548, 2023. [ bib | DOI | pdf | video  ]
[9]	Quantitative Verification and Strategy Synthesis for BDI Agents. Blair Archibald, Muffy Calder, Michele Sevegnani, and Mengwei Xu*. In Proceedings of NASA Formal Methods, pages 241-259, 2023. [ bib | DOI | pdf | slides  ]
[8]	Verifying BDI Agents in Dynamic Environments. Blair Archibald, Muffy Calder, Michele Sevegnani, and Mengwei Xu*. In Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering, pages 136-141, 2022. [ bib | DOI | pdf | slides  ]
[7]	Modelling and Verifying BDI Agents with Bigraphs. Blair Archibald, Muffy Calder, Michele Sevegnani, and Mengwei Xu*. In Science of Computer Programming, 215:102760, 2022. [ bib | DOI | pdf ]
[6]	Probabilistic BDI Agents: Actions, Plans, and Intentions. Blair Archibald, Muffy Calder, Michele Sevegnani, and Mengwei Xu*. In Proceedings of Software Engineering and Formal Methods (SEFM'21), pages 262-281. Springer International Publishing, 2021. (acceptance rate 25%) [ bib | DOI  | pdf | slides  ]
[5]	Observable and Attention-Directing BDI agents for Human-Autonomy Teaming. Blair Archibald, Muffy Calder, Michele Sevegnani, and Mengwei Xu*. In Proceedings of Third Workshop on Formal Methods for Autonomous Systems (FMAS'21), Electronic Proceedings in Theoretical Computer Science, volume 348, pages 167-175. Open Publishing Association, 2021. [ bib | DOI | pdf | slides ]
[4]	Extending BDI Agents with Robust Program Execution, Adaptive Plan Library, and Efficient Intention Progression. Mengwei Xu*. PhD Thesis, 2020. [ bib | URL | pdf ]
[3]	Intention Interleaving via Classical Replanning. Mengwei Xu*, Kevin McAreavey, Kim Bauters, and Weiru Liu. In Proceedings of the 31st IEEE International Conference on Tools with Artificial Intelligence (ICTAI'19), pages 85-92, 2019. (acceptance rate 26%) [ bib | DOI | pdf | slides ]
[2]	A Framework for Plan Library Evolution in BDI Agent Systems. Mengwei Xu*, Kim Bauters, Kevin McAreavey, and Weiru Liu. In Proceedings of the 30th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'18), pages 414-421, 2018. (acceptance rate 29%) [ bib | DOI | pdf | slides ]
[1]	A Formal Approach to Embedding First-Principles Planning in BDI Agent Systems. Mengwei Xu*, Kim Bauters, Kevin McAreavey, and Weiru Liu. In Proceedings of International Conference on Scalable Uncertainty Management, pages 333-347. Springer International Publishing, 2018. [ bib | DOI | pdf | slides ]

Tools

1. CAN-verify: a fully automatic tool that supports syntactic error checking, simulation, and verification of BDI agents .

Professional activities

Member of Autonomy and Verification Group.

Part of the following programme committees: AAMAS2023, AAMAS2024, ECAI2023, ECAI2024, FMAS2022, FMAS2023, NFM2024.

Reviewers of the following journals: ACM Transaction on Autonomous and Adaptive Systems, IEEE IoT Journal Review, IEEE Transactions on Cybernetics.

Employment

Sep 2023 - Current: Lecturer at School of Computing at the University of Newcastle.

Jan 2023 - Aug 2023: Research Fellow at Department of Computer Science at the University of Manchester.

Jun 2020 - Dec 2022: Research Associate at School of Computing Science at the University of Glasgow.

Education

2020: PhD in Computer Science at University of Bristol.

2016: First Class Honours in Mathematics at Queen’s University of Belfast.

2016: Bachelor Degree in Mathematics and Applied Mathematics at Anhui University of Finance Economics.

---