STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Chenjun, Zhou, Zhennan, Su, Zhan, Howe, Bill, Wang, Lucy Lu, Wen, Bingbing
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.13165