arxiv
PublishedMay 22, 2026 at 4:00 AM
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Publisher summary· verbatim
arXiv:2605.11739v3 Announce Type: replace Abstract: On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level mechanisms underl
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivLoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling7harxivAPPO: Agentic Procedural Policy Optimization7harxivALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing7harxivGrounding Computer Use Agents on Human Demonstrations7hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗