ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback
This addresses the problem of inefficient cooperation in multi-agent AI systems, offering a novel method for improving collaboration, though it is incremental in applying existing techniques to a specific domain.
The paper tackled the challenge of promoting prosocial behavior in multi-agent systems by developing ProToM, an AI system that provides targeted feedback based on Theory of Mind, resulting in higher success rates, shorter task completion times, and user preference over baselines.
While humans are inherently social creatures, the challenge of identifying when and how to assist and collaborate with others - particularly when pursuing independent goals - can hinder cooperation. To address this challenge, we aim to develop an AI system that provides useful feedback to promote prosocial behaviour - actions that benefit others, even when not directly aligned with one's own goals. We introduce ProToM, a Theory of Mind-informed facilitator that promotes prosocial actions in multi-agent systems by providing targeted, context-sensitive feedback to individual agents. ProToM first infers agents' goals using Bayesian inverse planning, then selects feedback to communicate by maximising expected utility, conditioned on the inferred goal distribution. We evaluate our approach against baselines in two multi-agent environments: Doors, Keys, and Gems, as well as Overcooked. Our results suggest that state-of-the-art large language and reasoning models fall short of communicating feedback that is both contextually grounded and well-timed - leading to higher communication overhead and task speedup. In contrast, ProToM provides targeted and helpful feedback, achieving a higher success rate, shorter task completion times, and is consistently preferred by human users.