CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
CAT:面向大型推理模型高效推理的置信度自适应思考
机构 * Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China(电子科技大学智能协同计算实验室) ; Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province(四川省泛在智能与可信服务重点实验室)
专题命中 复杂问题求解 :reasoning(title,abstract);CoT(abstract,abstract_cn);chain-of-thought(abstract);分类 cs.CL、cs.AI
AI总结 提出置信度自适应思考(CAT)框架,利用模型内在自确信信号作为置信度,通过偏好优化自主调节推理长度,在保持准确率的同时压缩简单问题的推理开销。
Comments Accepted at ACL 2026 Industry Track