一作ACL 2026Poster· ACL Industry Track
E fficient T ool: A Cost-Effective Aligning Framework for Tool-Conditioned Agents in SME Scenarios
Yuanqi Mu · Bingfeng Pi · Defei Xia · Lei Zuo · Yongqi Zhang
摘要
Large language models (LLMs) are increasingly adopted in downstream industries, yet aligning proprietary agents remains challenging due to limited high-quality data and hardware constraints in small and medium-sized enterprises (SMEs).We propose EfficientTool, a cost-effective, tool-conditioned a...