Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Muhua, Zhao, Qinlin, Yi, Xiaoyuan, Xie, Xing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.10665
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915669357887488
author Huang, Muhua
Zhao, Qinlin
Yi, Xiaoyuan
Xie, Xing
author_facet Huang, Muhua
Zhao, Qinlin
Yi, Xiaoyuan
Xie, Xing
contents As Large Language Models (LLM) based multi-agent systems become increasingly prevalent, the collective behaviors, e.g., collective intelligence, of such artificial communities have drawn growing attention. This work aims to answer a fundamental question: How does diversity of values shape the collective behavior of AI communities? Using naturalistic value elicitation grounded in the prevalent Schwartz's Theory of Basic Human Values, we constructed multi-agent simulations where communities with varying numbers of agents engaged in open-ended interactions and constitution formation. The results show that value diversity enhances value stability, fosters emergent behaviors, and brings more creative principles developed by the agents themselves without external guidance. However, these effects also show diminishing returns: extreme heterogeneity induces instability. This work positions value diversity as a new axis of future AI capability, bridging AI ability and sociological studies of institutional emergence.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
Huang, Muhua
Zhao, Qinlin
Yi, Xiaoyuan
Xie, Xing
Artificial Intelligence
As Large Language Models (LLM) based multi-agent systems become increasingly prevalent, the collective behaviors, e.g., collective intelligence, of such artificial communities have drawn growing attention. This work aims to answer a fundamental question: How does diversity of values shape the collective behavior of AI communities? Using naturalistic value elicitation grounded in the prevalent Schwartz's Theory of Basic Human Values, we constructed multi-agent simulations where communities with varying numbers of agents engaged in open-ended interactions and constitution formation. The results show that value diversity enhances value stability, fosters emergent behaviors, and brings more creative principles developed by the agents themselves without external guidance. However, these effects also show diminishing returns: extreme heterogeneity induces instability. This work positions value diversity as a new axis of future AI capability, bridging AI ability and sociological studies of institutional emergence.
title On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
topic Artificial Intelligence
url https://arxiv.org/abs/2512.10665