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

arXiv:2310.10701v3 Announce Type: replace
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 …

abstract agent agents arxiv collaboration collaborations cs.ai cs.cl game inference language language models large language large language models llm llms mind multi multi-agent performance planning reasoning replace study tasks text theory theory of mind tom type via while