Communities
Connect sessions
AI calendar
Organizations
Contact Sales
Search
Open menu
Home
Papers
2509.26628
Cited By
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
30 September 2025
Runze Liu
Jiakang Wang
Yuling Shi
Zhihui Xie
Chenxin An
Kaiyan Zhang
Jian Zhao
Xiaodong Gu
Lei Lin
Wenping Hu
Xiu Li
Fuzheng Zhang
Guorui Zhou
Kun Gai
OffRL
LRM
Re-assign community
ArXiv (abs)
PDF
HTML
HuggingFace (11 upvotes)
Github (952★)
Papers citing
"Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models"
1 / 1 papers shown
Title
MixReasoning: Switching Modes to Think
Haiquan Lu
Gongfan Fang
Xinyin Ma
Qi Li
Xinchao Wang
LRM
0
0
0
07 Oct 2025
1