When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

21 May 2025

Author Contacts:

rzzhu.nju@gmail.com yiliu07.nju@gmail.com sunzq@nju.edu.cn wangyw.evan@gmail.com whu@nju.edu.cn

ArXiv (abs)PDF HTML

Papers citing "When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning"

12 / 12 papers shown

Title
Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models Yule Liu Jingyi Zheng Zhen Sun Zifan Peng Wenhan Dong Zeyang Sha Shiwen Cui Weiqiang Wang Xinlei He OffRL LRM 95 9 0 18 Apr 2025
Reasoning Models Can Be Effective Without Thinking Wenjie Ma Jingxuan He Charlie Snell Tyler Griggs Sewon Min Matei A. Zaharia ReLM LRM 107 46 1 14 Apr 2025
Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution Chenghao Li Chaoning Zhang Yi Lu Jing Zhang Qigan Sun X. Wang Jiwei Wei Guoqing Wang Yang Yang Jikang Cheng LRM 120 2 0 13 Apr 2025
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Yang Sui Yu-Neng Chuang Guanchu Wang Jiamu Zhang Tianyi Zhang ... Hongyi Liu Andrew Wen Shaochen Zhong Hanjie Chen OffRL ReLM LRM 182 86 0 20 Mar 2025
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning Yuxiao Qu Matthew Y. R. Yang Amrith Rajagopal Setlur Lewis Tunstall E. Beeching Ruslan Salakhutdinov Aviral Kumar OffRL 138 38 0 10 Mar 2025
Chain of Draft: Thinking Faster by Writing Less Silei Xu Wenhao Xie Lingxiao Zhao Pengcheng He AI4TS LRM 150 76 0 25 Feb 2025
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning Wenkai Yang Shuming Ma Yankai Lin Furu Wei LRM 94 45 0 25 Feb 2025
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs Xingyu Chen Jiahao Xu Tian Liang Zhiwei He Jianhui Pang ... Zizhuo Zhang Rui Wang Zhaopeng Tu Haitao Mi Dong Yu LRM ReLM 169 168 0 30 Dec 2024
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models Sihang Li Houcheng Jiang Kun Wang Yunshan Ma Shi Jie Xiangnan He Tat-Seng Chua Tat-seng Chua KELM 121 61 0 03 Oct 2024
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Charlie Snell Jaehoon Lee Kelvin Xu Aviral Kumar LRM 176 644 0 06 Aug 2024
KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation Xindi Luo Zequn Sun Jing-xin Zhao Zhe Zhao Wei Hu KELM 53 7 0 22 Mar 2024
Training Verifiers to Solve Math Word Problems K. Cobbe V. Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun ... Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse John Schulman ReLM OffRL LRM 285 4,408 0 27 Oct 2021