Towards Simulating Social Influence Dynamics with LLM-based Multi-agents

TL;DR

This paper explores how large language model-based multi-agent systems can simulate human social behaviors like conformity and polarization, revealing how model size and reasoning ability affect social influence dynamics.

Contribution

It introduces a structured framework for simulating social influence with LLM-based agents and analyzes the impact of model scale and reasoning capabilities on social behaviors.

Findings

Smaller models show higher conformity rates.

Models optimized for reasoning resist social influence more.

Simulation framework effectively reproduces social dynamics.

Abstract

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.