混合推理：模式切换以思考

摘要

推理模型通过逐步解决问题的方式提升性能，将问题分解为子问题，并在生成答案之前探索长链的思维过程。然而，将扩展推理应用于每一步会引入大量冗余，因为子问题的难度和复杂性差异显著：少数关键步骤对最终答案具有真正的挑战性和决定性，而其他许多步骤仅涉及直接的修正或简单的计算。因此，一个自然的想法是赋予推理模型适应这种变化的能力，而不是对所有步骤采用相同的详细程度。为此，我们提出了MixReasoning框架，该框架在单个响应中动态调整推理的深度。由此产生的思维链便成为对困难步骤的详细推理与对简单步骤的简洁推理的混合体。在GSM8K、MATH-500和AIME上的实验表明，MixReasoning缩短了推理长度，并在不牺牲准确性的前提下显著提高了效率。

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.

混合推理：模式切换以思考

MixReasoning: Switching Modes to Think

摘要

Support