Theory of Mind Using Active Inference: A Framework for Multi-Agent Cooperation
This addresses scalable multi-agent cooperation for AI systems, though it appears incremental as an extension of active inference with recursive reasoning.
The paper tackles multi-agent cooperation by implementing Theory of Mind within active inference, enabling agents to infer others' beliefs from observable behavior without task-specific shared models or explicit communication. Results from collision avoidance and foraging simulations show ToM agents cooperate better by avoiding collisions and reducing redundant efforts compared to non-ToM counterparts.
Theory of Mind (ToM) -- the ability to understand that others can have differing knowledge and goals -- enables agents to reason about others' beliefs while planning their own actions. We present a novel approach to multi-agent cooperation by implementing ToM within active inference. Unlike previous active inference approaches to multi-agent cooperation, our method neither relies on task-specific shared generative models nor requires explicit communication. In our framework, ToM-equipped agents maintain distinct representations of their own and others' beliefs and goals. ToM agents then use an extended and adapted version of the sophisticated inference tree-based planning algorithm to systematically explore joint policy spaces through recursive reasoning. We evaluate our approach through collision avoidance and foraging simulations. Results suggest that ToM agents cooperate better compared to non-ToM counterparts by being able to avoid collisions and reduce redundant efforts. Crucially, ToM agents accomplish this by inferring others' beliefs solely from observable behaviour and considering them when planning their own actions. Our approach shows potential for generalisable and scalable multi-agent systems while providing computational insights into ToM mechanisms.