@inproceedings{ling-etal-2026-neural,
    title = "Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models",
    author = "Ling, Guoming  and
      Huang, Zhongzhan  and
      Lin, Yupei  and
      Li, Junxin  and
      Zhong, Shanshan  and
      Wu, Hefeng  and
      Lin, Liang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1149/",
    pages = "22900--22933",
    ISBN = "979-8-89176-395-1",
    abstract = "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{\%}. We will make our code and data publicly available."
}