Hugging Peers

Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

☆ Save
Liu, Xinyu,Jiao, Kechen,Xiao, Chunyang,Zhao, Runsong,Ruan, Junhao,Li, Bei,Liu, Jiahao,Wang, Qifan
+5 more authors show fewer
Chen, Xin,Wang, Jingang,Wang, Chenglong,Xiao, Tong,Zhu, JingBo
Findings of the Association for Computational Linguistics: EMNLP 2026
published

Abstract

No abstract available.

Cite this paper

@article{xinyu2026,
  title = {Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence},
  author = {Liu, Xinyu and Jiao, Kechen and Xiao, Chunyang and Zhao, Runsong and Ruan, Junhao and Li, Bei and Liu, Jiahao and Wang, Qifan and Chen, Xin and Wang, Jingang and Wang, Chenglong and Xiao, Tong and Zhu, JingBo},
  journal = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year = {2026},
  month = {Jan},
  doi = {10.18653/2026.findings-emnlp.1172},
  url = {https://doi.org/10.18653/2026.findings-emnlp.1172},
}