用人类团队经验优化大模型多智能体系统，发现扁平结构更高效。
Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamics
- 借鉴人类团队科学，构建含结构、多样性与交互动态的多智能体框架。
- 扁平团队在4个任务中表现优于层级团队，多样性影响复杂。
- 适合研究多智能体协作、社会推理或人机协同的学者参考。
以大型语言模型为驱动的多智能体系统日益受到关注，但其团队动态研究仍较少。受人类团队科学启发，我们提出一个涵盖结构、多样性与交互动态的多智能体框架，评估其在四个任务（CommonsenseQA、StrategyQA、Social IQa、Latent Implicit Hate）中的表现，覆盖常识与社会推理。结果表明，扁平团队整体表现优于层级团队，而多样性的影响具有复杂性。访谈显示，智能体对团队表现过于自信，但事后反思表明它们既认可协作价值，也面临对话协调不足等整合挑战。
原文摘要 · Abstract (English)
Multi-Agent Systems (MAS) with Large Language Model (LLM)-powered agents are gaining attention, yet fewer studies explore their team dynamics. Inspired by human team science, we propose a multi-agent framework to examine core aspects of team science: structure, diversity, and interaction dynamics. We evaluate team performance across four tasks: CommonsenseQA, StrategyQA, Social IQa, and Latent Implicit Hate, spanning commonsense and social reasoning. Our results show that flat teams tend to perform better than hierarchical ones, while diversity has a nuanced impact. Interviews suggest agents are overconfident about their team performance, yet post-task reflections reveal both appreciation for collaboration and challenges in integration, including limited conversational coordination.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。