作者位次 #4/7ACL 2026Findings· Findings of ACL
T ool CPT : Improving Tool Utilization in LLM Agents via Continuous Pre-training
Yifan Yang · Jinghui Lu · Evadeng · Ao Yang · Peijie Yu · TingHao YU · feng zhang
摘要
Autonomous agents powered by large language models (LLM-based agents) are capable of using off-the-shelf tools to interact with the environment, solve real-world problems, and boost work efficiency. However, current approaches to enhancing tool use for LLM-based agents primarily focus on post-tra...