{
  "id": 18254,
  "url": "https://arxiv.org/abs/2608.09836v1",
  "title": "Mismatch Matters: On-Policy Distillation Beyond Token Agreement",
  "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 mainly categorized into two types: student-excess tokens and student-deficit tokens. Student-excess tokens",
  "authors": "Zichao Yu, Chengzhi Yu, Shengze Xu, Yujin Han, Bingqing Jiang, Xu Wang, Difan Zou",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T16:53:14.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18254",
  "original_url": "https://arxiv.org/abs/2608.09836v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}