一作ACL 2026Findings· Findings of ACL
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
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 introd...