Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911691441176576 |
|---|---|
| author | Huang, Zixuan Xia, Xin Ren, Yuxi Zheng, Jianbin Wang, Xuanda Zhang, Zhixia Xie, Hongyan Liang, Songshi Chen, Zehao Xiao, Xuefeng Zhuang, Fuzhen Li, Jianxin Wang, Deqing Ban, Yikun |
| author_facet | Huang, Zixuan Xia, Xin Ren, Yuxi Zheng, Jianbin Wang, Xuanda Zhang, Zhixia Xie, Hongyan Liang, Songshi Chen, Zehao Xiao, Xuefeng Zhuang, Fuzhen Li, Jianxin Wang, Deqing Ban, Yikun |
| contents | Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. Recent studies show that longer reasoning chains are frequently uncorrelated with correctness and can even be detrimental to accuracy. In a further in-depth analysis of this phenomenon, we surprisingly uncover and empirically verify that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms. Motivated by this, we introduce SAGE (Self-Aware Guided Efficient Reasoning), a novel sampling paradigm that unleashes this efficient reasoning potential. Furthermore, integrating SAGE as mixed sampling into group-based reinforcement learning (SAGE-RL) enables SAGE-RL to effectively incorporate SAGE-discovered efficient reasoning patterns into standard pass@1 inference, markedly enhancing both the reasoning accuracy and efficiency of LRMs across multiple challenging mathematical benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08354 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Does Your Reasoning Model Implicitly Know When to Stop Thinking? Huang, Zixuan Xia, Xin Ren, Yuxi Zheng, Jianbin Wang, Xuanda Zhang, Zhixia Xie, Hongyan Liang, Songshi Chen, Zehao Xiao, Xuefeng Zhuang, Fuzhen Li, Jianxin Wang, Deqing Ban, Yikun Artificial Intelligence Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. Recent studies show that longer reasoning chains are frequently uncorrelated with correctness and can even be detrimental to accuracy. In a further in-depth analysis of this phenomenon, we surprisingly uncover and empirically verify that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms. Motivated by this, we introduce SAGE (Self-Aware Guided Efficient Reasoning), a novel sampling paradigm that unleashes this efficient reasoning potential. Furthermore, integrating SAGE as mixed sampling into group-based reinforcement learning (SAGE-RL) enables SAGE-RL to effectively incorporate SAGE-discovered efficient reasoning patterns into standard pass@1 inference, markedly enhancing both the reasoning accuracy and efficiency of LRMs across multiple challenging mathematical benchmarks. |
| title | Does Your Reasoning Model Implicitly Know When to Stop Thinking? |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.08354 |