{
  "id": 11914,
  "url": "https://arxiv.org/abs/2607.16850",
  "title": "Group Entropy-Controlled Policy Optimization",
  "summary": "Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm is often conducted on mixtures of heterogeneous tasks, which induce distinct entropy regimes under the same policy, making global or token-level entropy regulation insufficient to corresponding heterogeneous needs of exploration. This heterogeneity further makes GRPO-style normalized advantages i",
  "authors": "Guangran Cheng, Chengqi Lyu, Songyang Gao, Wenwei Zhang, Kai Chen",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T20:00:00.000Z",
  "fetched_at": "2026-07-21T05:10:12.656Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/11914",
  "original_url": "https://arxiv.org/abs/2607.16850",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}