研究权威角色如何影响大模型多智能体对话，发现专家型权威最有效。
Belief in Authority: Impact of Authority in Multi-Agent Evaluation Framework
- 基于权力理论分类权威角色，分析其在12轮对话中的影响
- 专家和参照型权威比合法型权威影响力更强，且无需主动服从
- 权威需明确表态才能产生影响，中立回应无效，适合设计不对称协作系统
采用大语言模型的多智能体系统常赋予特定角色以权威性来提升表现，但权威偏见对智能体交互的影响尚未深入探讨。本文首次通过ChatEval对自由形式多智能体评估中的角色化权威偏见进行系统分析。基于French和Raven的权力理论，将权威角色分为合法型、参照型和专家型，并考察其在12轮对话中的作用。实验使用GPT-4o与DeepSeek R1发现，专家型与参照型权力角色的影响力显著强于合法型角色。关键在于，权威偏见并非源于普通智能体的主动顺从，而是权威角色持续保持立场，而普通角色表现出灵活性所致。此外，权威影响依赖清晰的立场表达，中立回应无法引发偏见。这些发现为设计具有非对称互动模式的多智能体框架提供了重要启示。
原文摘要 · Abstract (English)
Multi-agent systems utilizing large language models often assign authoritative roles to improve performance, yet the impact of authority bias on agent interactions remains underexplored. We present the first systematic analysis of role-based authority bias in free-form multi-agent evaluation using ChatEval. Applying French and Raven's power-based theory, we classify authoritative roles into legitimate, referent, and expert types and analyze their influence across 12-turn conversations. Experiments with GPT-4o and DeepSeek R1 reveal that Expert and Referent power roles exert stronger influence than Legitimate power roles. Crucially, authority bias emerges not through active conformity by general agents, but through authoritative roles consistently maintaining their positions while general agents demonstrate flexibility. Furthermore, authority influence requires clear position statements, as neutral responses fail to generate bias. These findings provide key insights for designing multi-agent frameworks with asymmetric interaction patterns.
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。