{
  "id": 11908,
  "url": "https://arxiv.org/abs/2607.17247",
  "title": "Distilled Reinforcement Learning for LLM Post-training",
  "summary": "Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new",
  "authors": "Chen Wang, Zhaochun Li, Jionghao Bai, Yining Zhang, Hexuan Deng, Ge Lan",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-18T20:00:00.000Z",
  "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/11908",
  "original_url": "https://arxiv.org/abs/2607.17247",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}