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

arXiv: https://arxiv.org/abs/2605.25929 · HTML: https://mlsanity.com/paper/2605.25929/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 39 of its 62 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 39)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application](https://mlsanity.com/paper/2412.17481/) (2024)
- [Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity](https://mlsanity.com/paper/2502.08788/) (2025)
- [Explainability in Human-Agent Systems](https://mlsanity.com/paper/1904.08123/) (2019)
- [Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks](https://mlsanity.com/paper/2409.19338/) (2024)
- [Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets](https://mlsanity.com/paper/2604.02460/) (2026)
- [Spectral Graph Pruning Against Over-Squashing and Over-Smoothing](https://mlsanity.com/paper/2404.04612/) (2024)
- [A Tutorial on Modeling and Analysis of Dynamic Social Networks. Part I](https://mlsanity.com/paper/1701.06307/) (2017)
- [GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring](https://mlsanity.com/paper/2502.04891/) (2025)
- [Novel Multidimensional Models of Opinion Dynamics in Social Networks](https://mlsanity.com/paper/1505.04920/) (2015)
- [Are GATs Out of Balance?](https://mlsanity.com/paper/2310.07235/) (2023)
- [Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM](https://mlsanity.com/paper/2603.18507/) (2026)
- [Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph](https://mlsanity.com/paper/2409.11504/) (2024)
- [GATE: How to Keep Out Intrusive Neighbors](https://mlsanity.com/paper/2406.00418/) (2024)
- [When Shift Happens - Confounding Is to Blame](https://mlsanity.com/paper/2505.21422/) (2025)
- [On the Two Sides of Redundancy in Graph Neural Networks](https://mlsanity.com/paper/2310.04190/) (2023)

## Abstract (arXiv)

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.