{"ID":2868110,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17000","arxiv_id":"2509.17000","title":"Adaptive Overclocking: Dynamic Control of Thinking Path Length via Real-Time Reasoning Signals","abstract":"Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method that makes the overclocking hyperparameter $α$ dynamic and context-aware. Our method adjusts reasoning speed in real time through two complementary signals: (1) token-level model uncertainty for fine-grained step-wise control, and (2) input complexity estimation for informed initialization. We implement this approach with three strategies: Uncertainty-Aware Alpha Scheduling (UA-$α$S), Complexity-Guided Alpha Initialization (CG-$α$I), and a Hybrid Adaptive Control (HAC) that combines both. Experiments on GSM8K, MATH, and SVAMP show that HAC achieves superior accuracy-latency trade-offs, reducing unnecessary computation on simple problems while allocating more resources to challenging ones. By mitigating overthinking, Adaptive Overclocking enhances both efficiency and overall reasoning performance.","short_abstract":"Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method that makes the overclocking hyperparameter $α$ dynamic and context-aware. Our m...","url_abs":"https://arxiv.org/abs/2509.17000","url_pdf":"https://arxiv.org/pdf/2509.17000v1","authors":"[\"Shuhao Jiang\",\"Songbo Wang\",\"Yang Qiao\",\"Chun Xu\",\"Chaoyang Zheng\",\"Shengyi Zhou\",\"Huanjun Wang\",\"Fangming Li\",\"Cong Zhang\",\"Jiyu Wang\"]","published":"2025-09-21T09:40:27Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}