作者位次 #4/8ACL 2026Findings· Findings of ACL
Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models
Canhui Wu · Qiong Cao · Chang Li · Zhenfang Wang · Chao Xue · Yuwei Fan · Wei Xi · Xiaodong He
摘要
Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as “overthinking.” Existing solutions via reinforcement learning (RL) typically penalize generated tokens to promote conciseness. However, these methods encounter two cha...