Signals 4 · free daily AI digest

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper recorded by Signals 4 on 2026-08-31 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-31 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.LG · 机器学习 · first seen 2026-09-01

Abstract

On-policy distillation (OPD) offers dense token-level supervision as an alternative to the sparse outcome-level advantages of reinforcement learning with verifiable rewards (RLVR). However, the teacher scores student-generated trajectories that are inherently off-policy for it, so the reliability of its supervision, and hence the source of the student's improvement, remains unclear. We quantitativ

Read on arXiv →

#180 most recent of 215 cs.LG papers we have recorded · ↑ newer: Segmentation of Bovid Dentition Under Imperfect Annotations: A Compara · ↓ older: Rotational Equivariance in Machine Learning: A Comprehensive Tutorial
Cite this page: Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement: the #180 most recent of 215 cs.LG papers we have recorded (as of 2026-08-31). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/does-on-policy-distillation-really-distill-from-noisy-teacher-to-self-improvemen.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions