对比多种投票机制，发现多数决易导致低效协作。
RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration
- 对比不同投票规则在多轮协作中的表现
- 全票通过比最优方法初始性能低87%
- 语言早停策略可减少50%轮次且更接近理想性能
有效的群体决策对多智能体系统（MAS）至关重要。然而，不同共识机制如何影响协作质量和效率仍缺乏研究。本文在去中心化设置下系统性研究了群体决策机制。通过控制实验，分析不同投票规则对多轮协作中决策质量与效率的影响。结果表明，多数决因严格接受标准常导致协作低效；极端情况下，全票通过的初始性能比最佳方法低87%。对跨智能体通信的定性分析显示，消息长度随时间增加84%，且与上一轮相似度达90%。基于此，基于语言的早停方法使性能接近理想值13%，同时减少50%协作轮次。研究揭示了群体决策在优化MAS协作中的关键作用。
原文摘要 · Abstract (English)
Effective group decision-making is critical in Multi-Agent Systems (MAS). Yet, how different mechanisms for reaching consensus impact collaboration quality and efficiency remains understudied. We conduct a systematic study on group decision-making mechanisms in a decentralized setting. Through controlled experiments, we analyze how different voting rules affect decision quality and efficiency in a multi-round collaboration. Results reveal that majority voting often cause inefficient collaboration due to its strict acceptance criteria. At the extreme, unanimous voting gives 87% lower initial performance than the best-performing method. Our qualitative analysis of cross-agent communication shows that messages become longer and more repetitive over time: while message length increases by 84%, similarity to the previous round increases to 90%. Based on these insights, language-based early stopping methods make the performance 13% closer to oracle while reducing rounds by 50%. Our findings highlight the crucial role of group decision-making in optimizing MAS collaboration.
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。