一作ACL 2026Poster· Natural Language Processing
SAT : Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
Weiyang Huang · Xuefeng Bai · Kehai Chen · Xinyang Chen · Yibin Chen · Weili Guan · Min Zhang
摘要
Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive “overthinking”, generating unnecessarily long reasoning chains. While current solutions improve token efficiency, they often sacrifice fine-grained control or risk disrupting the logical integr...