作者位次 #4/6ACL 2026Findings· Findings of ACL
EMTIR - GRPO : Efficient Multi-Tool Augmented Large Language Models via Reinforcement Learning
Shixin Jiang · Zhihao Zhu · Jiafeng Liang · Yang Wu · Ming Liu · Bing Qin
摘要
Tool-integrated reasoning (TIR) enables large language models (LLMs) to invoke external tools for tasks beyond their internal capacity but often suffers from tool overuse.Existing approaches leverage imitation learning or reward shaping to improve efficiency, yet mainly target single-tool scenari...