{
  "id": 4576,
  "url": "https://arxiv.org/abs/2605.10194v1",
  "title": "TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment",
  "summary": "On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged context. We find that when this guidance spans the full response, all-token KL spends gradients on mostly redundant positions and amplifies privileged-information leakage, causing entropy rise, shortened reasoning, and out-of-distribution degradation in long-horizon math training. We propose Token-Routed Alignment for Critical rEasoning (TRACE),",
  "authors": "Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen, Yulan Hu, Zheng Pan, Xin Li et al.",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-11T08:45:03.000Z",
  "fetched_at": "2026-07-14T16:31:08.353Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4576",
  "original_url": "https://arxiv.org/abs/2605.10194v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}