{
  "id": 15838734,
  "title": "Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation",
  "url": "https://urgent.news/2026/10/20/capable-teacher-myopic-scorer-reward-free-teacher-repair-for-agentic",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-20T17:40:08.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.28586v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every token. A natural explanation of where it goes wrong is compounding error: the student's mistakes carry its trajectories beyond the region where the teacher is reliable, so recent methods keep training inside that region, through episode-length curricula, teacher-guided turns, prefix…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}