Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

2026-05-25

AI Summary

This study investigates how individual predictive capabilities and collaborative mechanisms jointly shape dynamic influence and enhance collective performance in multi-agent large language model negotiation. We propose the first formulation of the negotiation process as an input-dependent mixture-of-experts system grounded in the Friedkin–Johnsen opinion dynamics framework, demonstrating that an agent’s latent competence governs its influence. To make this competence observable, we introduce confidence level and alignment with initial opinions as proxy variables. Experimental results show that when the routing mechanism accurately reflects agents’ true capabilities, the system significantly outperforms both single-agent baselines and static ensemble approaches, thereby validating the effectiveness of our influence modeling and dynamic routing strategy.

Abstract

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.

Problem

• Multi-Agent Systems
• Influence
• Opinion Dynamics
• Mixture of Experts
• Agent Competence

Innovation

• Multi-Agent Systems
• Mixture of Experts
• Friedkin-Johnsen Dynamics
• Opinion Dynamics
• Agent Influence