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.

翻译：大型语言模型（LLM）凭借其广泛的世界知识和在语言相关任务上的熟练能力，已成为推理、规划与决策制定的重要工具。因此，LLM在多智能体系统中具有巨大的潜力，可通过自然语言交互促进协作。然而，LLM智能体倾向于过度报告并遵从任何指令，这可能导致多智能体协作中的信息冗余与混乱。受人类组织结构的启发，本文引入一个框架，通过基于提示的组织结构对LLM智能体施加约束以缓解这些问题。通过一系列具身LLM智能体及人机协作实验，我们的结果凸显了指定领导角色对团队效率的影响，揭示了LLM智能体所展现的领导特质及其自发的协作行为。此外，我们利用LLM的潜力，通过一个“批评-反思”过程提出增强的组织提示，从而构建出能降低通信成本并提升团队效率的新型组织结构。