Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

NeurIPSSpotlight2025

Authors: Yue Wang, Qiuzhi Liu, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Long reasoning models (LRMs) such as OpenAI's o1 and DeepSeek's R1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep thinkin…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

reasoning

← All NeurIPS 2025 Spotlight papers · Browse the whole archive