Embodied LLM Agents Learn to Cooperate in Organized Teams

TL;DR

This paper presents a framework for organizing embodied LLM agents into cooperative teams using prompt-based structures, improving efficiency and reducing communication costs in multi-agent systems.

Contribution

It introduces a novel prompt-based organization framework for LLM agents, inspired by human organizations, to enhance cooperation and team efficiency.

Findings

Designated leadership improves team efficiency.

Organizational prompts reduce communication costs.

Criticize-Reflect process enhances organizational structures.

Abstract

Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for natural language interaction within multi-agent systems to foster cooperation. However, LLM agents tend to over-report and comply with any instruction, which may result in information redundancy and confusion in multi-agent cooperation. Inspired by human organizations, this paper introduces a framework that imposes prompt-based organization structures on LLM agents to mitigate these problems. Through a series of experiments with embodied LLM agents and human-agent collaboration, our results highlight the impact of designated leadership on team efficiency, shedding light on the leadership qualities displayed by LLM agents and their spontaneous cooperative behaviors. Further, we harness the potential of LLMs to propose enhanced organizational prompts, via a Criticize-Reflect process, resulting in novel organization structures that reduce communication costs and enhance team efficiency.