Network Formation and Dynamics Among Multi-LLMs
This work addresses the need to understand AI behavior in social contexts, with implications for social simulation and AI system design, though it is incremental in benchmarking LLMs against human decisions.
The study tackled the problem of whether large language models (LLMs) exhibit human-like network dynamics in social interactions, finding that LLMs consistently reproduce key micro- and macro-level network principles such as preferential attachment and community structure, with alignment confirmed by a human-subject survey.
Social networks profoundly influence how humans form opinions, exchange information, and organize collectively. As large language models (LLMs) are increasingly embedded into social and professional environments, it is critical to understand whether their interactions approximate human-like network dynamics. We develop a framework to study the network formation behaviors of multiple LLM agents and benchmark them against human decisions. Across synthetic and real-world settings, including friendship, telecommunication, and employment networks, we find that LLMs consistently reproduce fundamental micro-level principles such as preferential attachment, triadic closure, and homophily, as well as macro-level properties including community structure and small-world effects. Importantly, the relative emphasis of these principles adapts to context: for example, LLMs favor homophily in friendship networks but heterophily in organizational settings, mirroring patterns of social mobility. A controlled human-subject survey confirms strong alignment between LLMs and human participants in link-formation decisions. These results establish that LLMs can serve as powerful tools for social simulation and synthetic data generation, while also raising critical questions about bias, fairness, and the design of AI systems that participate in human networks.