{
  "id": 14545,
  "url": "https://arxiv.org/abs/2607.26057",
  "title": "Pass the Baton: Trajectory-Relayed On-Policy Distillation",
  "summary": "On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute. We identify a teacher-student continuation asymmetry on failed prefixes, where the teacher tends to redirect while the student continues along the original direction, and con",
  "authors": "Haolei Xu, Xiaowen Xu, Haiwen Hong, Zixuan Ni, Hongxing Li, Yiwen Qiu",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-27T20:00:00.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/14545",
  "original_url": "https://arxiv.org/abs/2607.26057",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}