{
  "id": 14601101,
  "title": "Recovering Reliable Supervision via Critique-Guided On-Policy Distillation",
  "url": "https://urgent.news/2026/10/14/recovering-reliable-supervision-via-critique-guided-on-policy",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-14T17:54:34.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.20572v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recoverability of the teacher and show it fails on incorrect rollouts: the teacher follows student errors, although it recognizes them. We propose CriticOPD, using…",
  "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."
}