超越对齐：多文化智能体系统中价值多样性作为集体属性

摘要

多文化多智能体系统正日益部署于全球多样化的场景中，其中不同智能体植根于不同文化背景。现有文化评估聚焦于价值对齐：即单个智能体与目标文化的契合程度。然而，对齐本质上是单一智能体属性，无法揭示系统作为一个整体是否保留了其本应代表的文化多元性。我们提出将价值多样性作为多文化智能体系统的系统级评估维度，其定义基于文化条件化的智能体在共享价值调查中回答的差异性。借助世界价值观调查，我们在广泛的系统配置下评估了19种文化与18个基础模型。研究发现，多样性与对齐在很大程度上不相关，表明两者捕捉了互补的系统属性，且当前多文化智能体系统在价值多样性上显著低于人类社会。混合基础模型系统缩小了这一差距但并未完全弥合，该差距在不同文化组合与智能体规模下持续存在。社会互动进一步通过驱使智能体趋向共识而削弱多样性，参与式预算案例研究表明，这种同质化缩小了集体决策的广度。综上所述，我们的研究将价值多样性确立为多文化多智能体系统的独立评估维度，并揭示了当前基于大语言模型的社会中持续存在的同质化趋势。我们的代码与数据已公开于 https://github.com/iNLP-Lab/MultiAgent-Diversity。

English

Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural backgrounds. Existing cultural evaluation focuses on value alignment: how closely a single agent matches a target culture. Yet alignment is a per-agent property and cannot reveal whether a system, taken as a whole, preserves the cultural plurality it is meant to represent. We propose value diversity as a system-level evaluation axis for multicultural agent systems, defined through the dissimilarity between culturally conditioned agents' responses on a shared value survey. Using the World Values Survey, we evaluate 19 cultures and 18 backbone models across a wide range of system configurations. We find that diversity is largely uncorrelated with alignment, indicating that the two capture complementary system properties, and that current multicultural agent systems fall substantially below human societies in value diversity. Mixed-backbone systems narrow this gap but do not close it, and the gap persists across culture compositions and agent scales. Social interaction further erodes diversity by driving agents toward consensus, and a participatory budgeting case study shows that this homogenization narrows the breadth of collective decision-making. Together, our results establish value diversity as a distinct evaluation axis for multicultural multi-agent systems and reveal a persistent homogenization tendency in current LLM-based societies. Our code and data are publicly available at https://github.com/iNLP-Lab/MultiAgent-Diversity.