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

A new framework called CoevolveSim, introduced by researchers in an arXiv preprint (arXiv:2607.27512v1), shows that introducing finetuned specialist large language models (LLMs) more than doubles the shift in consensus belief in networked LLM populations, while persona-style role assignment and network structure have minimal effect on population-level consensus. The study, based on 1,280 controlled simulations across four scenarios, two network structures, and 20 medical-indication statements, indicates that realistic simulation of belief diffusion in multi-agent LLM systems requires a diverse set of underlying LLMs, not just persona prompting.

arXiv:2607.27512v1 Announce Type: new Abstract: 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.