探索价值观多样性如何影响多智能体AI社区的集体行为。
On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
- 基于舒瓦茨价值理论构建多智能体仿真，研究价值观多样性对集体行为的影响。
- 适度的价值多样性提升稳定性与创造性，极端差异导致系统不稳定。
- 揭示了价值观多样性作为未来AI能力的新维度，适合关注AI社会性与制度生成的研究者。
随着基于大语言模型的多智能体系统日益普及，此类人工社区的集体行为（如集体智慧）受到越来越多关注。本文旨在回答一个根本问题：价值观多样性如何塑造人工智能社区的集体行为？基于广泛接受的舒瓦茨基本人类价值观理论，我们构建了多智能体模拟实验，让不同数量的智能体在开放互动和制度形成中协作。结果表明，适度的价值多样性能增强价值观稳定性，促进涌现行为，并催生出无需外部指导的创造性原则。然而，这些效应存在边际递减：极端异质性会引发系统不稳定性。本工作将价值观多样性定位为未来AI能力的新维度，连接了AI能力与制度生成的社会学研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。