让大模型自动提前结束推理，又快又准。
Dynamic Early Exit in Reasoning Models
- 根据模型自信度动态决定是否提前终止推理链
- 平均缩短推理序列40%以上，准确率提升0.3%~5.0%
- 无需训练，可直接用于现有推理大模型
近期大型推理语言模型（LRLMs）依赖测试时扩展，通过延长思维链（CoT）生成来解决复杂任务。然而，过长的思维链不仅降低求解效率，还因过度详细或冗余的推理步骤导致准确率下降。本文提出一种简单有效的自终止方法：在生成过程中监测潜在推理转折点，当模型对某个试答表现出高置信度时，动态终止后续推理链的生成。该方法无需额外训练，可无缝集成至现有的 o1 类推理模型。在10个推理基准（如GSM8K、MATH-500、AMC、GPQA、AIME和LiveCodeBench）上的实验表明，该方法在11种不同系列与规模的先进推理模型上均表现稳定，使思维链长度平均减少19.1%至80.1%，同时准确率提升0.3%至5.0%。
原文摘要 · Abstract (English)
Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of problem solving, but also risks accuracy loss due to the extremely detailed or redundant reasoning steps. We propose a simple yet effective method that allows LLMs to self-truncate CoT sequences by early exit during generation. Instead of relying on fixed heuristics, the proposed method monitors model behavior at potential reasoning transition points and dynamically terminates the next reasoning chain's generation when the model exhibits high confidence in a trial answer. Our method requires no additional training and can be seamlessly integrated into existing o1-like reasoning LLMs. Experiments on 10 reasoning benchmarks (e.g., GSM8K, MATH-500, AMC, GPQA, AIME and LiveCodeBench) show that the proposed method is consistently effective on 11 cutting-edge reasoning LLMs of varying series and sizes, reducing the length of CoT sequences by an average of 19.1% to 80.1% while improving accuracy by 0.3% to 5.0%.
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。