作者位次 #7/8ACL 2026Findings· Findings of ACL
ARM 2: Adaptive Reasoning Model with Vision Understanding and Executable Code
Jian Xie · Zhendong Chu · Aoxiao Zhong · Kai Zhang · Mingzhe Han · Xing fan · Jialie Shen · Qingsong Wen
摘要
Large Reasoning Models (LRMs) often suffer from the “over-thinking” problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitigate this issue, such as length penalties or routing mechanisms, but they are typically heuristic and task-specific, lack...