Rethinking Thinking Steps in Overthinking: Towards More Effective Reasoning
TL;DR
This work proposes a training-free, interpretable framework that selects thinking words via attention heads to guide LRMs toward more effective reasoning, and consistently outperforms the strong baseline DEER.
Abstract
Understanding overthinking in large reasoning models (LRMs) is crucial for interpretability as well as reasoning efficiency and effectiveness. However, existing approaches primarily adopt coarse-grained reasoning strategies, such as truncating Chains-of-Thought or switching reasoning modes, which reduce verbosity but are insufficient to actively guide reasoning toward more effective trajectories. To address these issues, we propose a training-free, interpretable framework that selects thinking words via attention heads to guide LRMs toward more effective reasoning. Specifically, we categorize thinking steps into effective and redundant states, identify the attention head that best discriminates between them as the Thinking Partition Head to construct an Effective Thinking Representation Space, and compute the Information Gain Ratio (IGR) between candidate thinking words and this space to select the word that steers reasoning toward a more effective direction. Extensive experiments on mathematical and scientific reasoning benchmarks, including AIME24, AMC23, MATH-500, GSM8K, and GPQA-D, show that our method consistently outperforms the strong baseline DEER, achieving average improvements of 1.2–1.3% in accuracy and 2.5–4.5% in compression rate. Compared to vanilla baselines, our approach yields larger gains of 2.6–6.3% in accuracy while reducing token usage by 22–43%.