# Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models

arXiv: https://arxiv.org/abs/2607.27512 · HTML: https://mlsanity.com/paper/2607.27512/

## Key facts

- Cited by 1 papers in the map (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 18 of its 62 references that are in the map.
- First posted on arXiv 29 Jul 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, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data](https://mlsanity.com/paper/2410.01560/) (2024)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [Med42-v2: A Suite of Clinical LLMs](https://mlsanity.com/paper/2408.06142/) (2024)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [The Widespread Adoption of Large Language Model-Assisted Writing Across Society](https://mlsanity.com/paper/2502.09747/) (2025)
- [The Persuasive Power of Large Language Models](https://mlsanity.com/paper/2312.15523/) (2023)
- [Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media](https://mlsanity.com/paper/2412.18148/) (2024)
- [Social Influence and the Collective Dynamics of Opinion Formation](https://mlsanity.com/paper/1311.3475/) (2013)
- [Can LLM Agents Maintain a Persona in Discourse?](https://mlsanity.com/paper/2502.11843/) (2025)
- [Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits](https://mlsanity.com/paper/2605.18890/) (2026)
- [The Trilemma of Truth in Large Language Models](https://mlsanity.com/paper/2506.23921/) (2025)
- [Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems](https://mlsanity.com/paper/2605.07069/) (2026)
- [The Effect of Belief Boxes and Open-mindedness on Persuasion](https://mlsanity.com/paper/2512.06573/) (2025)

## Built on by (most cited first, 1 of 1)

- [Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents](https://mlsanity.com/paper/2610.02654/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among interacting LLMs remain poorly understood. We introduce CoevolveSim, a framework for studying belief diffusion within networked LLM populations. CoevolveSim allows us to isolate and study three factors: domain specialization, social-role assignment, and social network structure. Within this framework, generalist and specialist LLM agents exchange and revise beliefs. In each round, an LLM agent observes a summary of its neighbors' beliefs before updating its own. We run 1,280 controlled simulations spanning four scenarios, two network structures, and 20 medical-indication statements. We find that persona-style role assignment and network structure reshape individual belief revision but have minimal effect on population-level consensus. In contrast, introducing (finetuned) specialist LLMs more than doubles the shift in consensus and gives rise to consistent asymmetries in exerted influence. We further show that simple persistence-based opinion-dynamics models reproduce collective outcomes in all-generalist LLM populations, whereas heterogeneous LLM populations require population-level belief composition to reproduce consensus and agent identity to predict individual belief transitions. Our results indicate that realistic simulation of belief diffusion in multi-agent LLM systems requires a diverse set of underlying LLMs, not persona prompting alone.