Back to papers
September 23, 2026cs.LGcs.AI

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

Jie Zhang, Jingxiao Yang, Zhehao Huang, Yuhang Liu, Xiaolin Huang
Read on arXivDownload PDF
Categories

cs.LG, cs.AI

When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through | One9Founders