Signals 4 · free daily AI digest

When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment

Paper recorded by Signals 4 on 2026-09-23 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.AI · 人工智能 · first seen 2026-09-24

Abstract

Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance on individual tokens. On-policy distillation (OPD) supplies dense feedback on student-generated responses, yet teacher preference need not reflect correctness. Recent hybrids combine OPD and verifier-derived advantages or reweight task credit using

Read on arXiv →

#8 most recent of 380 cs.AI papers we have recorded · ↑ newer: Learning Holographic Reduced Representations with Clifford Variational · ↓ older: Shopping by algorithm: How agentic AI deploys human heuristics as a su
Cite this page: When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment: the #8 most recent of 380 cs.AI papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/when-and-where-to-trust-the-teacher-unifying-on-policy-distillation-and-grpo-thr.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI 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