This page shows all events ABCP (co-)organised and will be (co-)organising. Some events (co-)sponsored or supported by ABCP may also be included.
Scalable and Adaptive Cooperative AI: From Networked Systems to Language Agents
Abstract
As AI systems increasingly interact with humans and other agents, their effectiveness depends on their ability to cooperate. This requires learning from local information, coordinating at scale, and adapting to unfamiliar environments and other agents’ behaviour. The challenge becomes more complex when participants pursue different objectives and individual incentives conflict with collective outcomes.
In this talk, Dr Du will present the work on scalable and adaptive cooperative AI. The talk will begin with multi-agent reinforcement learning for networked systems, showing how local interaction structure can support efficient learning at scale, and how causal representations can help agents adapt to new environmental dynamics with limited experience. Then Dr Du will turn to social dilemmas, introducing SocialJax and recent work on OpenSocialJax. These environments allow researchers to investigate whether language-model agents can discover hidden environmental rules through repeated interaction while adapting to other agents. Examples involving shared resources and environmental maintenance raise a central question: does a better understanding of the environment lead to sustained cooperation?
Together, these studies connect scalable learning with environmental and social adaptation. Dr Du will conclude the talk by discussing how learned capabilities, structural assumptions and incentives shape cooperative behaviour, and the open challenges of robustness and safety when deploying multi-agent systems in the real world.
Speaker
Yali Du, Associate Professor, King’s College London
Chair
Shujun Li, Professor of Cyber Security, University of Kent, London and South East University Group
Bio
Dr Yali Du is an Associate Professor in AI at King’s College London and a Turing Fellow at The Alan Turing Institute. She leads the Cooperative AI Lab, where she develops cooperative, safe and human-aligned AI for complex decision-making. Her research spans scalable multi-agent learning, human–AI coordination and value alignment.
She received the AAAI New Faculty Highlights Award in 2023 and was named a Rising Star in AI by KAUST. Her collaborative research received Responsible AI UK AI & Robotics Best Research Paper Awards in 2026. She serves as an Associate Editor for IEEE Transactions on Artificial Intelligence and a Guest Editor for Autonomous Agents and Multi-Agent Systems, and has held area chair, senior area chair and organising roles at major international AI conferences.
How to join remotely (MS Teams)
Meeting ID: 334 824 266 758 155
Passcode: kj9qs9uN