{
  "id": 15861,
  "url": "https://arxiv.org/abs/2607.26246",
  "title": "Weak-to-Strong On-Policy Distillation",
  "summary": "On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs. Prevailing approaches assume a teacher at least as capable as the student: they either distill a larger model into a smaller one, which fails at the frontier where no larger teacher exists, or consolidate multiple domain experts trained from a shared base, which requires costly training at the student's",
  "authors": "Fangxu Yu, Zinan Lin, Xiaodong Liu, Weijia Xu, Michael Xu, Tianyi Zhou",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-27T20:00:00.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/15861",
  "original_url": "https://arxiv.org/abs/2607.26246",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}