Lune

ACL Findings2026

Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models

Guoming Ling, Zhongzhan Huang, Yupei Lin, Junxin Li, Shanshan Zhong, Hefeng Wu, Liang Lin

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%. Our code and data are available on Github.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement cites Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning
  • Graph of Thoughts: Solving Elaborate Problems with Large Language Models cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • Graph of Thoughts: Solving Elaborate Problems with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Logical Phase Transitions: Understanding Collapse in LLM Logical ReasoningXinglang Zhang, Yunyao Zhang, ZeLiang Chen, Junqing Yu et al.ACL 2026 · 28 citations
  2. AttnPO: Attention-Guided Process Supervision for Efficient ReasoningShuaiyi Nie, Siyu Ding, Wenyuan Zhang, Linhao Yu et al.ACL 2026 · 21 citations
  3. One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query RefinementYixiao Zhou, Dongzhou Cheng, Zhiliang Wu, Yi Yang et al.ACL 2026 · 3 citations

Builds on102

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  3. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  4. Graph of Thoughts: Solving Elaborate Problems with Large Language ModelsMaciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger et al.AAAI 2024 · 1,292 citations
  5. SimPO: Simple Preference Optimization with a Reference-Free RewardYu Meng, Mengzhou Xia, Danqi ChenNeurIPS 2024 · 1,203 citations

Related papers

  1. On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case StudyRiccardo Alberghi, Elizaveta Demyanenko, Luca Biggio, Luca SagliettiNeurIPS 2025 · 2 citations
  2. What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought ReasoningGangwei Jiang, Yahui Liu, Zhaoyi Li, Wei Bi et al.EMNLP 2025
  3. Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM ReasoningZhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang et al.ICML 2025
  4. C3oT: Generating Shorter Chain-of-Thought Without Compromising EffectivenessYu Kang, Xianghui Sun, Liangyu Chen, Wei ZouAAAI 2025 · 162 citations
  5. A Formal Comparison Between Chain of Thought and Latent ThoughtKevin Xu, Issei SatoICML 2026 · 12 citations
Dusk over the sea between two cliffs drawn in fine vertical lines