Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning
This provides a low-resource solution for users of LLMs that lack built-in tool calling, though it is incremental as it builds on existing prompt engineering techniques.
The paper tackles the problem of enabling stable tool calling in locally deployed and some commercial LLMs without fine-tuning, achieving a 100% success rate across multiple models and tasks using only prompt engineering and code design.
Currently, the vast majority of locally deployed open-source large language models (LLMs) and some commercial model interfaces do not support stable tool calling functionality. The existing solution involves fine-tuning LLMs, which results in significant time and computational resource consumption. This paper proposes a method that enables LLMs to achieve stable tool calling capabilities using only prompt engineering and some ingenious code design. We conducted experiments on multiple LLMs that lack tool calling capabilities across various tool calling tasks, achieving a success rate of 100%.