Network Effects and Agreement Drift in LLM Debates

ArXi:2604.11312v1 Announce Type: cross Large Language Models (LLMs) have nstrated an unprecedented ability to simulate human-like social behaviors, making them useful tools for simulating complex social systems. However, it remains unclear to what extent these simulations can be trusted to accurately capture key social mechanisms, particularly in highly unbalanced contexts involving minority groups. This paper uses a network generation model with controlled homophily and class sizes to examine how LLM agents behave collectively in multi-round debates.