多智能体系统像专家混合模型，谁有影响力取决于其真实能力与表达自信的结合。
Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?
- 用弗里德金-约翰森模型分析智能体间意见动态，揭示影响力机制
- 智能体表现依赖输入，系统整体效果随能力路由而提升
- 可用自评信心、感知信心和观点一致度作为影响力的可观察代理
多智能体大模型辩论的有效性不仅取决于个体预测，还依赖于沟通与协作方式。我们通过弗里德金-约翰森（FJ）意见动态模型研究这一机制，该模型可解析多智能体系统中的固执、影响力与意见变化，且能捕捉实际观察到的辩论模式。研究表明，FJ参数具有输入依赖性，使多智能体辩论成为一种专家混合模型。这意味着当路由策略反映智能体能力时，多智能体系统可超越单个智能体和静态集成。由于能力在实践中不可见，我们分析了可通过观测代理建立影响力的特征：智能体的自评信心、被感知的信心，以及初始观点与其他智能体的一致性。
原文摘要 · Abstract (English)
The effectiveness of multi-agent LLM deliberation depends not only on the agents' individual predictions, but also on how they communicate and collaborate. We study this mechanism through the lens of Friedkin-Johnsen (FJ) opinion dynamics, a tractable model for analyzing stubbornness, influence, and opinion change in multi-agent systems that captures empirically observed deliberation patterns. We show that the FJ parameters are input-dependent, turning multi-agent deliberation into a mixture of experts. This perspective implies that multi-agent systems can outperform single agents and static ensembles when routing reflects agent competence. Since competence is latent in practice, we analyze how influence is established through observable proxies: agents' self-assessed confidence, their perceived confidence, and initial alignment with other agents' views.
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。