CORTEXA
← Browse
arxivcs.CLcs.AI2026-07-01

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

Qizhi Jiang, Shuo Wang, Pei Ke, Yuhang Song, Ke Qin

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.

View free PDFSource page

Related papers

arxivcs.CLcs.AI2026-07-19

Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph

Peiji Yu, Xin Chen, Tianxing Wu

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) h…

View free PDFSource page
arxivcs.LGcs.AIcs.CLcs.MA2026-07-20

MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models

Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov, Zifeng Ding, Volker Tresp, Yunpu Ma

Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that spe…

View free PDFSource page
arxivcs.CLcs.AI2026-06-25

ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models

Xin Lin, Liang Zhang, Guoqi Ma, Hongyao Tu, Jinsong Su

Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications. The core challenge of OpenRE lies in achieving reliable generalization to unseen relation types. Current OpenRE approa…

View free PDFSource page
arxivcs.CLcs.AI2026-07-08

Future Confidence Distillation in Large Language Models

Sahil Kale

Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability. Existing approaches, however, l…

View free PDFSource page
arxivcs.AIcs.CL2026-07-11

SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models

Dongxu Zhang, Yiding Sun, Zihao Guo, Xiangyang Yang, Kai Tang, Lin Chen, et al.

Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may reflect missing capability, an unstable reasoning trajectory, or a failure to activate a reasoning s…

View free PDFSource page
arxivcs.CLcs.AI2026-07-16

Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models

Jungseob Lee, Seungyoon Lee, Suhyune Son, Dongyub Jude Lee, Sungbin Han, Sugyeong Eo, et al.

A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors. When sampling fails, a common fix shows the generator the gold ans…

View free PDFSource page