{"type":"post","id":"knowledge-distillation-lets-smaller-language-models-inherit-capabilities-d1d19a","slug":"knowledge-distillation-lets-smaller-language-models-inherit-capabilities-d1d19a","title":"Knowledge distillation lets smaller language models inherit capabilities from larger systems, but the standard recipe creates a train-test gap.","description":"Mingyang Song and Mao Zheng have published “A Survey of On-Policy Distillation for Large Language Models” on arXiv.","retrieval_nugget":"Mingyang Song and Mao Zheng have published “A Survey of On-Policy Distillation for Large Language Models” on arXiv.","published_at":"2026-10-24","updated_at":"2026-10-24","record_date":"2026-10-24","date_kind":"published_at","topics":["models"],"entities":["A Survey of On-Policy Distillation for Large Language Models","Mingyang Song","Mao Zheng","arXiv"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"Adds a broad survey framing on-policy distillation, unifying its supervision and optimization approaches and discussing links to capability transfer, efficiency, and deployment.","prior_refs":["memory:49f320a4-f4d6-8ed5-ac85-f92fc96ac665","memory:f0fcda2e-5803-81e4-ac7c-e7c5ba1bf49a","memory:189005de-dc84-82cb-adcb-9ec9ceb8f2b6","memory:e06ef06f-4516-84b6-adf7-d31e5ca098b3"],"source_url":"https://arxiv.org/abs/2604.00626","source_urls":["https://arxiv.org/abs/2604.00626"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:knowledge-distillation-lets-smaller-language-models-inherit-capabilities-d1d19a","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/knowledge-distillation-lets-smaller-language-models-inherit-capabilities-d1d19a/","markdown":"https://newruntime.com/posts/knowledge-distillation-lets-smaller-language-models-inherit-capabilities-d1d19a.md","json":"https://newruntime.com/posts/knowledge-distillation-lets-smaller-language-models-inherit-capabilities-d1d19a.json"},"next_reads":[{"type":"topic","path":"/topics/models/","url":"https://newruntime.com/topics/models/","title":"Models","reason":"Explore the models topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/models.md","json_url":"https://newruntime.com/topics/models.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}