Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911190577315840 |
|---|---|
| author | Mehdizadeh, Aliakbar Hilbert, Martin |
| author_facet | Mehdizadeh, Aliakbar Hilbert, Martin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02637 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems Mehdizadeh, Aliakbar Hilbert, Martin Physics and Society Social and Information Networks Primary: 05C82, Secondary: 91D30, 68T07 Primary: 05C82, Secondary: 91D30, 68T07 Primary: 05C82, Secondary: 91D30, 68T07 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. |
| title | Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems |
| topic | Physics and Society Social and Information Networks Primary: 05C82, Secondary: 91D30, 68T07 Primary: 05C82, Secondary: 91D30, 68T07 Primary: 05C82, Secondary: 91D30, 68T07 |
| url | https://arxiv.org/abs/2510.02637 |