作者位次 #4/8ACL 2026Poster· Natural Language Processing
A da M ix: Adaptive Mixing for Short and Long Reasoning Adapters
Hao Luo · Xiao Yan · Xinyan Li · Qiming Zeng · Yuhao Lin · Shanshan Feng · Hao Wang · Jiawei Jiang
摘要
Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by generating detailed Chain-of-Thought (CoT) reasoning. However, they tend to apply a uniform, computation-intensive deep reasoning strategy to all problems, leading to unnecessary overhead on simple tasks. This sign...