EfficientTool: A Cost-Effective Aligning Framework for Tool-Conditioned Agents in SME Scenarios

Yuanqi Mu, Bingfeng.Pi, Defei Xia, Lei.Zuo, Yongqi Zhang

Keywords: Tool-Augmented Agents, LLM Alignment, Parameter-Efficient Fine-Tuning, Experience Replay, SME Deployment

Abstract:

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 alignment framework forming a closed loop over data collection, iterative training, and deployment-oriented evaluation.
EfficientTool adopts a self-evolving bootstrapping-based Trajectory Collection Pipeline for high-quality trajectory generation, followed by iterative Model Training Pipeline using tool-conditioned parameter-efficient fine-tuning (PEFT).
We evaluate the model with Interaction and Evaluation Pipeline in public and private benchmarks, and deploy for an internal enterprise agent.
Results show that EfficientTool effectively aligns model in SME scenarios while preserving general tool-calling capability.

Submission Type: Deployed

Submission Number: 175