Search papers, labs, and topics across Lattice.
This study introduces CoevolveSim, a novel framework for analyzing belief diffusion among interacting large language models (LLMs) in multi-agent environments. By conducting 1,280 simulations across various scenarios, the authors reveal that while social-role assignment and network structure influence individual belief revision, the introduction of specialist LLMs significantly enhances consensus shifts and creates asymmetries in influence. The findings underscore the necessity of diverse LLM populations for accurately modeling belief dynamics, challenging the efficacy of persona-based prompting alone.
Specialist LLMs can more than double consensus shifts in belief diffusion, revealing critical asymmetries in influence that challenge conventional approaches.
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.
