arXiv — cs.AI preprintsInternational5 October 2026
Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation
This is an official announcement record
Firsthand records what arXiv — cs.AI preprints announced and links to the original. The wording below is theirs, not ours.
arXiv:2610.02678v1 Announce Type: new Abstract: On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher, but providing such supervision for every rollout requires substantial teacher computation. We introduce Success-Referenced On-Policy Distillation (SR-OPD), which reduces this cost by selecting which prompts and rollouts receive teacher supervision. When the student produces both successful and failed rollouts for the same prompt, a successful rollout can serve as a natural reference for selecting failed rollouts. SR-OPD therefore fo
Read the official announcement
Opens arxiv.org
More from arXiv — cs.AI preprints
- MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching5 October 2026
- Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses5 October 2026
- The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?5 October 2026
- Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation5 October 2026
- Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents5 October 2026
This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.