{
  "id": 10992,
  "url": "https://arxiv.org/abs/2607.13399",
  "title": "Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations",
  "summary": "On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We first clarify the role of OPD as an exploration catalyst: it steers the student toward correct reasoning paths via dense token-level guidance, without expanding capability ceiling. We confirm this by showing that prompt diversity matters more than per-problem sampling numbers, and",
  "authors": "Rui Wang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Wenhao Yu",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-14T20:00:00.000Z",
  "fetched_at": "2026-07-17T05:10:53.887Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/10992",
  "original_url": "https://arxiv.org/abs/2607.13399",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}