# Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems

arXiv: https://arxiv.org/abs/2510.02637 · HTML: https://mlsanity.com/paper/2510.02637/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2025.

## Built on by (most cited first, 8 of 8)

- [When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs](https://mlsanity.com/paper/2510.19107/) (2025)
- [Gender Dynamics and Homophily in a Social Network of LLM Agents](https://mlsanity.com/paper/2602.02606/) (2026)
- [Epistemic Substitution: How Grokipedia's AI-Generated Encyclopedia Restructures Authority](https://mlsanity.com/paper/2512.03337/) (2025)
- [Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions](https://mlsanity.com/paper/2606.04197/) (2026)
- [Collective Opinion Dynamics in Structured LLM Populations](https://mlsanity.com/paper/2604.11312/) (2026)
- [LLMs for Social Network Modeling: From Network Generation to Dynamic Processes](https://mlsanity.com/paper/2609.08049/) (2026)
- [Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric](https://mlsanity.com/paper/2609.18306/) (2026)
- [AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation](https://mlsanity.com/paper/2610.01705/) (2026)

## Abstract (arXiv)

This study examines how interactions among artificially intelligent (AI) agents, guided by large language models (LLMs), drive the evolution of collective network structures. We ask LLM-driven agents to grow a network by informing them about current link constellations. Our observations confirm that agents consistently apply a preferential attachment mechanism, favoring connections to nodes with higher degrees. We systematically solicited more than a million decisions from four different LLMs, including Gemini, ChatGPT, Llama, and Claude. When social attributes such as age, gender, religion, and political orientation are incorporated, the resulting networks exhibit heightened assortativity, leading to the formation of distinct homophilic communities. This significantly alters the network topology from what would be expected under a pure preferential attachment model alone. Political and religious attributes most significantly fragment the collective, fostering polarized subgroups, while age and gender yield more gradual structural shifts. Strikingly, LLMs also reveal asymmetric patterns in heterophilous ties, suggesting embedded directional biases reflective of societal norms. As autonomous AI agents increasingly shape the architecture of online systems, these findings contribute to how algorithmic choices of generative AI collectives not only reshape network topology, but offer critical insights into how AI-driven systems co-evolve and self-organize.