SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
This addresses efficiency issues in complex problem-solving for users of large reasoning models, though it is incremental as it builds on existing pruning methods.
The paper tackles the problem of 'overthinking' in Large Reasoning Models, where they generate unnecessarily long reasoning chains, by introducing the Stepwise Adaptive Thinking (SAT) framework, which achieves up to 40% reduction in reasoning tokens while generally maintaining or improving accuracy across 9 models and 7 benchmarks.
Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long reasoning chains. While current solutions improve token efficiency, they often sacrifice fine-grained control or risk disrupting the logical integrity of the reasoning process. To address this, we introduce Stepwise Adaptive Thinking (SAT), a framework that performs step-level, difficulty-aware pruning while preserving the core reasoning structure. SAT formulates reasoning as a Finite-State Machine (FSM) with distinct thinking modes (Slow, Normal, Fast, Skip). It navigates these states dynamically using a lightweight Process Reward Model (PRM), compressing easy steps while preserving depth for hard ones. Experiments across 9 LRMs and 7 benchmarks show that SAT achieves up to 40% reduction in reasoning tokens while generally maintaining or improving accuracy.