Skip to content
Open access

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

Jul 2026 · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · pp. 2271-2283 · 0 citations · 36 references
Computer Science

TL;DR

Confidence-Adaptive Thinking (CAT) is proposed, a framework that incorporates the model's intrinsic self-certainty signals as confidence into the preference optimization process, which autonomously modulates reasoning lengths based on problem difficulty.

Abstract

Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequently exhibit overthinking on simple queries, resulting in significant token overhead and reduced inference efficiency. However, existing compression methods predominantly apply uniform length reduction or rely on coarse-grained difficulty estimation, often leading to performance degradation on difficult problems. To address this limitation, we propose Confidence-Adaptive Thinking (CAT), a framework that incorporates the model's intrinsic self-certainty signals as confidence into the preference optimization process, which autonomously modulates reasoning lengths based on problem difficulty. Experimental results show that CAT consistently outperforms state-of-the-art baselines on reasoning accuracy across multiple benchmarks on different base models. Our work enables LRMs to effectively compress confident responses while deliberating on uncertain ones, offering a potentially robust solution for balancing accuracy and latency in practical industrial scenarios.

Read PDF

Similar papers

Preprint Jul 2026

OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping

OS-Pruner is a lightweight plug-in framework that formulates chain-of-thought pruning as an optimal stopping problem that achieves 20-60\% reduction in generation length with minimal accuracy sacrifice on diverse reasoning benchmarks and base models.

Mohammed Ehab, Aymane El Gadarri, Vivek F. Farias et al. · 0 citations
Preprint Jul 2026

EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization

Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such as fast-slow thinking switching and reasoning trajectory compression, fail to make a fine-grained distinction between beneficial and redundant steps within the LRM's reasoning process, and may thus impair reasoning capability in their pursuit of efficiency. To simultaneously improve reasoning efficiency and capability, we propose EvoThink, a framework that reduces redundant verification and encourages the exploration of new reasoning paths. EvoThink comprises two key components: Self-Pruning Training (SPT), an unsupervised method that iteratively prunes redundant reasoning steps and self-trains on the concise trajectories; and Aha-Moment Preference Optimization (AMPO), which, inspired by genetic algorithms, identifies valuable failed reasoning attempts, synthesizes from-wrong-to-right aha-moment data, and optimizes the model to internalize this reasoning pattern. Extensive evaluations across mathematical reasoning and code generation benchmarks demonstrate that EvoThink not only substantially reduces inference-time token usage but also improves the reasoning capability of LRMs.

Xinbang Dai, Zheyu Xin, Huikang Hu et al. · 0 citations
Conference Open access 2026

CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought

Overall, the findings establish that optimizing the thought process structure refines reasoning efficacy, with computational efficiency emerging as a derivative benefit of a clearer thought process.

Oded Schlesinger, Young Kyung Kim, J. Matias Di Martino et al. · 0 citations
Preprint Aug 2026

ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning

Chain-of-Thought (CoT) reasoning has significantly enhanced the multi-step problem-solving capabilities of large language models (LLMs) by introducing explicit intermediate reasoning. However, advanced Large Reasoning Models (LRMs) often exhibit overthinking behaviors, including excessively long reasoning steps, redundant steps, and high computational overhead. Existing token-length reward strategies aim to promote concise outputs, but often result in pseudo-conciseness, where token count is reduced, yet redundant reasoning persists, leading to longer and less structurally efficient chains. To address these limitations, we propose ChainPrune, a novel reasoning path semantic structural optimization method to efficiently and controllably synthesize self-generated high-quality training data. We initially consolidate self-generated reasoning paths into a tree-based structure, followed by a multi-criteria dominant path selection process for preference data construction that formulates shallow reasoning trajectories while preserving essential reasoning steps. To further enhance the quality of reasoning, we incorporate a DPO-based preference learning method combined with supervised loss, effectively mitigating false reward suppression. This innovative integration significantly enhances both the efficiency and effectiveness of our reasoning framework. Comprehensive experimental results demonstrate significant reductions in step length and computational overhead, while maintaining or even enhancing accuracy.

Weihang Pan, Zhengxu Yu, Yuxiang Zhang et al. · 1 citation
2025

Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

This work presents a theoretical framework that reveals how reasoning steps can amplify error through three failure modes: incorrect sub-task decomposition, incorrect sub-task solving, and incorrect final answer summarization, and introduces structured interventions that adapt CoT generation according to the identified failure types.

Haibo Jin, Peiyan Zhang, Man Luo et al. · 1 citation
Preprint Jul 2026

PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity

PoTRE (Poly-Topological Reasoning Ensembles), a heterogeneous framework that decouples inference into four agents that achieves improved reasoning performance using similar or fewer inference tokens compared to heavily scaled homogeneous baselines is introduced.

Anmol Kankariya, Sercan Ö. Arik · 0 citations