{
  "id": 527043,
  "title": "Mismatch Matters: On-Policy Distillation Beyond Token Agreement",
  "url": "https://urgent.news/2026/08/10/mismatch-matters-on-policy-distillation-beyond-token-agreement",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-10T16:53:14.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.09836v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses. We therefore shift our focus from agreement to teacher-student mismatch, and find that mismatch tokens can be…",
  "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."
}