让推理模型按难易程度自动调节思考深度，又快又准。
MixReasoning: Switching Modes to Think
- 动态调整每一步的思考深度，难处详尽、简单处简略。
- 在GSM8K等数据集上推理长度缩短30%以上，准确率不变。
- 适合需要高效推理的应用场景，如实时问答系统。
推理模型通过分步拆解问题并生成长链思维来提升性能，但对每一步都进行深度推理会造成大量冗余。由于子问题难度差异大，仅有少数关键步骤真正复杂，多数仅需简单计算或修改。为此，我们提出MixReasoning框架，使模型在单次响应中动态调整推理深度：对难点进行详细推理，对简单步骤采用简洁推断。在GSM8K、MATH-500和AIME上的实验表明，该方法显著缩短推理长度，大幅提升效率，且不牺牲准确性。
原文摘要 · Abstract (English)
Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to this variation, rather than treating all steps with the same level of elaboration. To this end, we propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response. The resulting chain of thought then becomes a mixture of detailed reasoning on difficult steps and concise inference on simpler ones. Experiments on GSM8K, MATH-500, and AIME show that MixReasoning shortens reasoning length and substantially improves efficiency without compromising accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。