Home » Authors » Zhenyue Peng, Lin Yang, Jie Wang, Xiaoqi Ni, Hanzhu Chen, Xize Liang, Yanjun Wu, Rujing Wang, Kaiwen Zhou, Jianye Hao

Zhenyue Peng, Lin Yang, Jie Wang, Xiaoqi Ni, Hanzhu Chen, Xize Liang, Yanjun Wu, Rujing Wang, Kaiwen Zhou, Jianye Hao

Public reference bibliography and cataloged PDF materials authored or published by Zhenyue Peng, Lin Yang, Jie Wang, Xiaoqi Ni, Hanzhu Chen, Xize Liang, Yanjun Wu, Rujing Wang, Kaiwen Zhou, Jianye Hao.

Found 1 document(s) Page 1 of 1

SteadyThought: Mitigating LLM Under-Thinking via Thought-Level Preference Optimization

Year: 2026 • Source: arxiv.org • Listed PDF

Flexible switching between reasoning trajectories (i.e., thought switching) has significantly enhanced the reasoning capabilities of Large Reasoning Models (LRMs). However, existing models often switch excessively yet fa...