Does Your Reasoning Model Implicitly Know When to Stop Thinking?
- URL: http://arxiv.org/abs/2602.08354v1
- Date: Mon, 09 Feb 2026 07:38:22 GMT
- Title: Does Your Reasoning Model Implicitly Know When to Stop Thinking?
- Authors: Zixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng, Xuanda Wang, Zhixia Zhang, Hongyan Xie, Songshi Liang, Zehao Chen, Xuefeng Xiao, Fuzhen Zhuang, Jianxin Li, Yikun Ban, Deqing Wang,
- Abstract summary: We show that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms.<n>Motivated by this, we introduce SAGE, a novel sampling paradigm that unleashes this efficient reasoning potential.
- Score: 45.954548163594204
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- From Long to Short: LLMs Excel at Trimming Own Reasoning Chains [48.692414597960244]
O1/R1 style large reasoning models (LRMs) signal a substantial leap forward over conventional instruction-following LLMs.<n>Recent studies show that LRMs are prone to suffer from overthinking.<n>We propose a test-time scaling method, EDIT, which efficiently guides LRMs to identify the shortest correct reasoning paths at test time.
arXiv Detail & Related papers (2025-09-07T19:00:44Z) - Promoting Efficient Reasoning with Verifiable Stepwise Reward [7.385337642642193]
Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning.<n>LRMs often suffer from overthinking, expending excessive computation on simple problems and reducing efficiency.<n>We propose a novel rule-based verifiable stepwise reward mechanism (VSRM), which assigns rewards based on the performance of intermediate states in the reasoning trajectory.
arXiv Detail & Related papers (2025-08-14T02:43:53Z) - Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey [8.736170026262279]
Large reasoning models (LRMs) like OpenAI o1 and DeepSeek R1 have demonstrated impressive performance on complex reasoning tasks.<n>These models also face a huge challenge that generating unnecessarily lengthy and redundant reasoning chains.
arXiv Detail & Related papers (2025-07-13T14:51:59Z) - Lost at the Beginning of Reasoning [85.17612793300238]
We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.
arXiv Detail & Related papers (2025-06-27T09:53:57Z) - Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs [8.359909829007005]
We investigate whether efficient reasoning strategies introduce behavioral inconsistencies in large reasoning models (LRMs)<n>$ICBENCH$ is a benchmark designed to measure inconsistency in LRMs across three dimensions.<n>We find that while larger models generally exhibit greater consistency than smaller ones, they all display widespread "scheming" behaviors.
arXiv Detail & Related papers (2025-06-24T10:25:28Z) - Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
arXiv Detail & Related papers (2025-06-18T17:18:12Z) - Efficient Inference for Large Reasoning Models: A Survey [74.17203483365171]
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason.<n>However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time.<n>This survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality.
arXiv Detail & Related papers (2025-03-29T13:27:46Z) - A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond [88.5807076505261]
Large Reasoning Models (LRMs) have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference.<n>A growing concern lies in their tendency to produce excessively long reasoning traces.<n>This inefficiency introduces significant challenges for training, inference, and real-world deployment.
arXiv Detail & Related papers (2025-03-27T15:36:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.