{
  "id": 521,
  "url": "https://arxiv.org/abs/2606.28182v1",
  "title": "LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior",
  "summary": "Embodied agents operating in decentralized and partially observable environments have attracted growing attention in recent years. However, existing large language model (LLM)-based agents often exhibit behaviors that are misaligned with their partners or inconsistent with the environment state, leading to inefficient cooperation and poor task success. To address this challenge, we propose a novel framework, Learning Laws of Cooperation (LLawCo), that enables embodied agents to autonomously alig",
  "authors": "Qinhong Zhou, Chuang Gan, Anoop Cherian",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-26T15:26:12.000Z",
  "fetched_at": "2026-07-14T14:14:37.245Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/521",
  "original_url": "https://arxiv.org/abs/2606.28182v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}