{
  "id": 1435,
  "url": "https://arxiv.org/abs/2606.05985v1",
  "title": "Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems",
  "summary": "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",
  "authors": "Shaoyang Xu, Jingshen Zhang, Long P. Hoang, Jinyuan Li, Wenxuan Zhang",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-04T10:26:33.000Z",
  "fetched_at": "2026-07-14T14:15:17.101Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1435",
  "original_url": "https://arxiv.org/abs/2606.05985v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}