让大模型像寻路一样找最优推理路径，又准又快。
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
- 将推理过程视为动态搜索，用双重启发式评估候选步骤。
- 准确率提升超3.5%，生成长度减少超22%。
- 适合需要高效精准推理的场景，如数学题、逻辑分析。
链式思维已显著提升大模型的问题求解能力。然而，现有模型生成推理步骤时缺乏前瞻性，常陷入冗余且次优的思维路径。本文提出神经链式思维搜索（NCoTS），将推理重构为寻找最优思维策略的动态搜索过程。通过量化表征解空间，我们发现存在稀疏但更优的推理路径，其准确率与简洁性均优于标准输出。该方法利用双因素启发式，评估候选推理算子，兼顾正确性与计算成本，主动导航至这些优质路径。NCoTS在多个推理基准上实现帕累托改进，准确率提升超过3.5%，生成长度减少超过22%。代码与数据见 https://github.com/MilkThink-Lab/Neural-CoT-Search。
原文摘要 · Abstract (English)
Chain-of-Thought reasoning has significantly enhanced the problem-solving capabilities of Large Language Models. Unfortunately, current models generate reasoning steps sequentially without foresight, often becoming trapped in suboptimal reasoning paths with redundant steps. In contrast, we introduce Neural Chain-of-Thought Search (NCoTS), a framework that reformulates reasoning as a dynamic search for the optimal thinking strategy. By quantitatively characterizing the solution space, we reveal the existence of sparse superior reasoning paths that are simultaneously more accurate and concise than standard outputs. Our method actively navigates towards these paths by evaluating candidate reasoning operators using a dual-factor heuristic that optimizes for both correctness and computational cost. Consequently, NCoTS achieves a Pareto improvement across diverse reasoning benchmarks, boosting accuracy by over 3.5% while reducing generation length by over 22%. Our code and data are available at https://github.com/MilkThink-Lab/Neural-CoT-Search.
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。