让大模型根据自信程度自动调节推理长度，既省资源又不丢准确率。
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
- 用模型自身信心值动态控制推理过程长短
- 在多个基准上比现有方法更准且更省token
- 适合需要平衡速度与准确率的工业部署场景
大型推理模型（LRMs）通过长思维链（CoT）轨迹在复杂任务中表现卓越，但对简单问题常出现过度推理，导致大量token开销并降低推理效率。现有压缩方法多采用统一长度缩减或粗粒度难度估计，常导致难题性能下降。为此，我们提出置信度自适应思考（CAT）框架，将模型内在自信心信号作为置信度融入偏好优化过程，自主调节不同难度问题的推理长度。实验表明，CAT在多个基准和不同基础模型上均持续优于当前最优基线，在推理准确性上表现更优。该工作使LRMs能在自信时压缩响应、在不确定时深入思考，为实际工业场景中平衡精度与延迟提供稳健解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。