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.

翻译：多元文化多智能体系统日益部署在全球多样化的场景中，不同智能体植根于不同的文化背景。现有的文化评估聚焦于价值对齐：即单一智能体与目标文化的匹配程度。然而，对齐是智能体层面的属性，无法揭示系统整体是否保留了其本应代表的多元文化。我们提出价值多样性作为多元文化智能体系统的系统级评估维度，通过衡量不同文化条件化智能体在共享价值调查中响应的差异性来定义。利用世界价值观调查，我们评估了19种文化和18个骨干模型在多种系统配置下的表现。我们发现，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，且当前多元文化智能体系统在价值多样性上显著低于人类社会。混合骨干系统缩小了这一差距但未能消除，且该差距在不同文化组合和智能体规模下持续存在。社会交互进一步通过驱使智能体趋向共识而侵蚀多样性，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。综合起来，我们的结果确立了价值多样性作为多元文化多智能体系统的独特评估维度，并揭示了当前基于大语言模型的社群中普遍存在的同质化趋势。我们的代码和数据已公开于 https://github.com/iNLP-Lab/MultiAgent-Diversity。