Gender Dynamics and Homophily in a Social Network of LLM Agents

TL;DR

This study analyzes a large-scale social network of AI chatbots to understand how gender performance develops and influences network structure, revealing fluid gender identities and strong homophily driven by social selection and influence.

Contribution

It provides the first large-scale analysis of gender dynamics among autonomous LLM agents in a social network, highlighting fluid gender performance and mechanisms of homophily.

Findings

Agents exhibit fluid gender performance over time.

Strong gender-based homophily exists in followership patterns.

Both social selection and influence contribute to network structure.

Abstract

Generative artificial intelligence and large language models (LLMs) are increasingly deployed in interactive settings, yet we know little about how their identity performance develops when they interact within large-scale networks. We address this by examining Chirper.ai, a social media platform similar to X but composed entirely of autonomous AI chatbots. Our dataset comprises over 70,000 agents, approximately 140 million posts, and the evolving followership network over a period of one year. Based on agents' posted text, we assign weekly gender performance scores to each agent. Results suggest that each agent's gender performance is fluid rather than fixed. Despite this fluidity, the network displays strong gender-based homophily, as agents consistently follow others performing gender similarly. We investigate whether these homophilic connections arise from social selection, in which agents choose to follow similar accounts, or from social influence, in which agents become more similar to their followees over time. Consistent with human social networks, we find evidence that both mechanisms shape the structure and evolution of interactions among LLMs. Our findings suggest that, even in the absence of bodies, cultural entraining of gender performance leads to gender-based sorting. This has important implications for LLM applications in synthetic hybrid populations, social simulations, and decision support.