Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
This work addresses the problem of simulating social influence for researchers in computational social science, but it is incremental as it builds on existing LLM capabilities.
The study investigated whether LLM-based multi-agent simulations can reproduce human social dynamics like conformity and polarization in online forums, finding that smaller models show higher conformity while reasoning-optimized models are more resistant to influence.
Recent advancements in Large Language Models offer promising capabilities to simulate complex human social interactions. We investigate whether LLM-based multi-agent simulations can reproduce core human social dynamics observed in online forums. We evaluate conformity dynamics, group polarization, and fragmentation across different model scales and reasoning capabilities using a structured simulation framework. Our findings indicate that smaller models exhibit higher conformity rates, whereas models optimized for reasoning are more resistant to social influence.