From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems
This work addresses the problem of creating reliable and socially beneficial AI systems for society, but it appears incremental as it builds on existing research without new breakthroughs.
The research group tackled the development of trustworthy autonomous systems and human-centred AI, highlighting key results in multiagent systems, but no specific outcomes or numbers were provided.
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.