一作ACL 2026Findings· Findings of ACL
A dap T hink: Adaptive Thinking Preferences for Reasoning Language Models
Wenyue Xu · Xu Wan · Wei Wang · Wenqi Huang · Wotao Yin · Shengjie Zhao · Mingyang Sun
摘要
The slow thinking paradigm has been widely validated to enhance the reasoning capabilities of Large Language Models (LLMs), but it introduces notable reasoning inefficiencies: models often overthink simple tasks while prematurely shifting their reasoning paths when addressing complex problems. To...