{
  "id": 2062155,
  "title": "Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning",
  "url": "https://urgent.news/2026/08/19/beyond-teacher-likelihood-group-calibrated-on-policy-distillation-for",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-19T17:54:58.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.19181v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, however, token-level teacher support can favor locally plausible responses that omit evidence distributed across the input or violate global task constraints. Task-specific verifiers, in contrast, evaluate task completion at the response level and may…",
  "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."
}