作者位次 #2/5ACL 2026Poster· Natural Language Processing
E quiv P runer: Boosting Efficiency and Quality in LLM -Based Search via Action Pruning
Jiawei Liu · Qisi Chen · Jianshu Zhang · Quan Liu · Defu Lian
摘要
Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration of semantically equivalent steps. Existing semantic similarity methods struggle to accurately identify such equivalenc...