I am a senior undergraduate student at the School of Computer Science and Technology, Huazhong University of Science and Technology (HUST). I am fortunate to be advised by Prof. Qinbin Li.
Upon receiving my B.Eng. degree in June 2026, I will continue my research journey at HUST as a Ph.D. student.
My research interests lie at the intersection of Large Language Models and Systems, with a specific focus on designing efficient agent frameworks.
Motivation Can we utilize statistical methods instead of relying heavily on LLM inference to select tools efficiently?
Contribution We propose AutoTool, which actively manages tool usage inertia via a Tool Inertia Graph. By selectively bypassing LLM inference, it reduces token consumption by up to 30% while maintaining competitive performance.