This paper presents a novel framework that leverages Large Language Models (LLMs) for multi-agent cooperation. The framework enables embodied agents to plan, communicate, and cooperate with other embodied agents or humans to efficiently accomplish long-horizon tasks. The research demonstrates that recent LLMs, such as GPT-4, can surpass strong planning-based methods and exhibit emergent effective communication using this framework without requiring fine-tuning or few-shot prompting. The study also reveals that LLM-based agents that communicate in natural language can earn more trust and cooperate more effectively with humans.
Publication date: July 5, 2023
Project Page: https://vis-www.cs.umass.edu/Co-LLM-Agents/
Paper: https://arxiv.org/pdf/2307.02485v1.pdf
