Open access
Jul 2026
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
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.
Qizhi Jiang, Shuoyao Wang, Pei Ke et al.
· Proceedings of the 64th Annu... · 0 citations