神经链式推理搜索：寻找最优推理路径以增强大语言模型
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
AI总结：
本文提出神经链式推理搜索框架，通过动态搜索最优推理策略提升大语言模型性能，实验表明在多个基准测试中准确率提升超3.5%，生成长度减少超22%。
摘要：
链式推理显著增强了大语言模型的问题解决能力。然而，当前模型生成推理步骤时缺乏前瞻性，常陷入冗余的次优路径。本文引入神经链式推理搜索（NCoTS）框架，将推理重新表述为动态搜索最优思维策略的过程。通过定量刻画解空间，揭示了同时更准确且简洁的稀疏优质推理路径的存在。我们的方法通过双因素启发式评估候选推理运算符，主动导航至这些路径。因此，NCoTS在多个推理基准测试中实现了帕累托改进，准确率提升超过3.5%，生成长度减少超过22%。我们的代码和数据可在https://github.com/MilkThink-Lab/Neural-CoT-Search获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
