{
  "id": 4653,
  "url": "https://arxiv.org/abs/2605.09128v1",
  "title": "Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design",
  "summary": "Multi-agent AI systems need behavioral constitutions, but it is unresolved whether such rules should emerge internally through agent self-governance or be discovered externally through optimization. We present the first controlled comparison of internal deliberation and external evolution across three social environments: a coordination grid-world, an iterated public goods game, and a bilateral trading market. Across 180 simulation runs, evolution significantly outperforms deliberation in collec",
  "authors": "Hershraj Niranjani, Ujwal Kumar, Phan Xuan Tan",
  "category": "research",
  "topics": "regulation,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-09T19:19:52.000Z",
  "fetched_at": "2026-07-14T16:31:08.357Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4653",
  "original_url": "https://arxiv.org/abs/2605.09128v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}