Findings of the Association for Computational Linguistics: ACL 2026
Figure 1: Motivation and Overview of our NCoTS. (a) Planning Bottleneck in Traditional CoT. (b) Importance of Path Planning. Sparse guiding tokens from a strong teacher significantly boost performance, confirming that path planning is the key bottleneck. (c) The NCoTS framework. Our method reformulates reasoning as a search process, employing a dual-factor heuristic to ac- tively discover paths that are both accurate and concise.
Overview
Reformulates reasoning as a dynamic search over thinking strategies. Candidate reasoning operators are evaluated with a dual-factor heuristic that balances correctness and computational cost.
