作者位次 #4/5ACL 2026Poster· ACL Industry Track
CAT : Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
Qizhi Jiang · Shuo Wang · Pei Ke · Yuhang Song · KE QIN
摘要
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 compressi...