{"paper":{"title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Fangming Cui, Jiahong Li, Sunan Li","submitted_at":"2026-05-18T09:47:53Z","abstract_excerpt":"On-Policy Self-Distillation (OPSD) introduces a unified learning framework in which a single large language model simultaneously serves as both teacher and student. Unlike conventional knowledge distillation that relies on a separate, often larger teacher model, OPSD operates under different contextual roles: the teacher policy is granted privileged access to verified reasoning traces, while the student policy observes only the problem statement. OPSD is trained to minimize per-token distributional divergence between the two roles over trajectories sampled from the student itself, thereby alig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18141","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18141/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.108959Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.382558Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5bdc4bf723982a07f976422a43f5d99244a2fce0d459e860f0b8fa77e7305339"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}