Does Your Reasoning Model Implicitly Know When to Stop Thinking?
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyReinforcement LearningSimilar Papers 제목 키워드 기반
Making the most of your day: online learning for optimal allocation of time
We study online learning for optimal allocation when the resource to be allocated is time. %Examples of possible applications include job scheduling for a computing server, a driver filling a day with rides, a landlord r…
SchedulingImplicitly Abusive Comparisons -- A New Dataset and Linguistic Analysis
We examine the task of detecting implicitly abusive comparisons (e.g. {``}Your hair looks like you have been electrocuted{''}). Implicitly abusive comparisons are abusive comparisons in which abusive words (e.g. {``}dumb…
Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?
Recent work shows that large language models (LLMs) can answer multiple-choice questions using only the choices, but does this mean that MCQA leaderboard rankings of LLMs are largely influenced by abilities in choices-on…
Graph MiningLanguage ModelingLanguage ModellingLarge Language Model+1The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes
When users receive either a positive or negative outcome from an automated system, Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes into positive ones by crossing a decision boundary…
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavior-level control, making them insufficien…