发现推理过程60%后答案基本稳定，可提前停止以降本增效。
Answer Convergence as a Signal for Early Stopping in Reasoning
- 通过答案一致性判断何时停止推理，避免冗余步骤。
- 在自然问答任务上减少40%以上token，准确率还提升。
- 适合追求高效推理的落地应用，尤其对资源敏感场景。
链式思考（CoT）提示虽增强大语言模型的推理能力，但常导致输出冗长，增加推理开销。本文系统研究最小必要推理量，发现数学类任务中模型在完成约60%推理步骤后即达最终答案，剩余内容存在显著冗余。基于此，提出三种推理时优化策略：（1）基于答案一致性的早期停止；（2）提升生成推理结束信号的概率；（3）利用内部激活学习停止时机的监督方法。在五个基准和五种开源权重大模型上实验表明，所提方法显著降低令牌消耗，准确率几乎无损。尤其在NaturalQuestions任务上，答案一致性策略减少超40%令牌，且准确率进一步提升。本工作强调推理效率的重要性，为实际应用提供可落地的推理优化方案。
原文摘要 · Abstract (English)
Chain-of-thought (CoT) prompting enhances reasoning in large language models (LLMs) but often leads to verbose and redundant outputs, thus increasing inference cost. We hypothesize that many reasoning steps are unnecessary for producing correct answers. To investigate this, we start with a systematic study to examine what is the minimum reasoning required for a model to reach a stable decision. We find that on math reasoning tasks like math, models typically converge to their final answers after 60\% of the reasoning steps, suggesting substantial redundancy in the remaining content. Based on these insights, we propose three inference-time strategies to improve efficiency: (1) early stopping via answer consistency, (2) boosting the probability of generating end-of-reasoning signals, and (3) a supervised method that learns when to stop based on internal activations. Experiments across five benchmarks and five open-weights LLMs show that our methods significantly reduce token usage with little or no accuracy drop. In particular, on NaturalQuestions, Answer Consistency reduces tokens by over 40\% while further improving accuracy. Our work underscores the importance of cost-effective reasoning methods that operate at inference time, offering practical benefits for real-world applications.
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。