Theory of Mind for Multi-Agent Collaboration via Large Language Models

Huao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Charles Michael Lewis, Katia P. Sycara

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: Interpretability, Interactivity, and Analysis of Models for NLP

Keywords: Large Language Models, Multi-Agent Reinforcement Learning, Theory of Mind

Abstract: While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi-Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limitations in LLM-based agents' planning optimization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these issues, finding that it enhances task performance and the accuracy of ToM inferences for LLM-based agents.

Submission Number: 4178