# Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs Source: [Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs]() Collection index: [llms.txt]() Data updated: 2026-03-04T05:00:05.079Z Authors: Jie Cao, Tianwei Lin, Zhenxuan Fan, Bo Yuan, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Siliang Tang Published: 2026-02-28T09:57:52.000Z ## Abstract Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a substantial increase in reasoning budget. Recent studies show that existing CoT paradigms tend to induce systematic overthinking, unnecessarily coupling reasoning capability with reasoning cost. Most prior approaches reduce token usage through post hoc techniques such as token compression, truncation, or length penalties, without explicitly addressing the core mechanisms of reasoning. We propose \\textbf{Draft-Thinking}, which guides models to first learn a concise \\textit{draft-style} reasoning structure that retains only the critical reasoning steps. Through a \\textit{progressive curriculum learning}, the model stably internalizes this efficient reasoning pattern as its capability scales. Moreover, Draft-Thinking introduces adaptive prompting, which elevates reasoning depth to a flexible, model-selectable behavior. Extensive experiments demonstrate that Draft-Thinking substantially reduces reasoning budget while largely preserving reasoning performance; for example, on MATH500, it achieves an 82.6\\% reduction in reasoning budget at the cost of only a 2.6\\% performance drop. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Mathematical Reasoning on AIME 2025 (Acc, Tokens, EFF)](): Mathematical Reasoning; AIME 2025; Accuracy: 64.79. - [Mathematical Reasoning on MinervaMath (Acc, Tokens, EFF)](): Mathematical Reasoning; MinervaMath; Accuracy: 53.68. - [Mathematical Reasoning on OlympiadBench (Acc, Tokens, EFF)](): Mathematical Reasoning; OlympiadBench; Accuracy: 69.19. - [Mathematical Reasoning on LiveMathBench 202505](): Mathematical Reasoning; LiveMathBench 202505; Accuracy: 31.83. - [Mathematical Reasoning on MATH 500 (Acc, Tokens, EFF)](): Mathematical Reasoning; MATH 500; Accuracy: 94.2. ## Original sources and implementation [Original paper]() [PDF]()