Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge Model

ArXi:2604.07816v1 Announce Type: new Tool learning has emerged as a promising paradigm for large language models (LLMs) to address real-world challenges. Due to the extensive and irregularly updated number of tools, tool retrieval for selecting the desired tool subset is essential. However, current tool retrieval methods are usually based on academic benchmarks containing overly detailed instructions (e.g., specific API names and parameters), while real-world instructions are vague. Such a discrepancy would hinder the tool retrieval in real-world applications.