Improving Tool Retrieval By Leveraging Large Language Models For Query Generation

Abstract

Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated factual knowledge, or taking actions in the real world. In such settings, in-context learning by providing a short list of relevant tools in the prompt is a viable approach. To retrieve relevant tools, various approaches have been suggested, ranging from simple frequency-based matching to dense embedding-based semantic retrieval. However, such approaches lack the contextual and common-sense understanding required to retrieve the right tools for complex user requests. Rather than increasing the complexity of the retrieval component itself, we propose leveraging LLM understanding to generate a retrieval query. Then, the generated query is embedded and used to find the most relevant tools via a nearest-neighbor search. We investigate three approaches for

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykachuee2024improving

Related papers

• Efficient And Scalable Estimation Of Tool Representations In Vector Space (2024)2.95
• An Interactive Multi-modal Query Answering System With Retrieval-augmented Large Language Models (2024)5.84
• Graph-based Retriever Captures The Long Tail Of Biomedical Knowledge (2024)0.00
• Large Language Models Are Built-in Autoregressive Search Engines (2023)13.49
• Don't Forget Private Retrieval: Distributed Private Similarity Search For Large Language Models (2023)5.24
• Talkplay-tools: Conversational Music Recommendation With LLM Tool Calling (2025)0.00
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• Lamra: Large Multimodal Model As Your Advanced Retrieval Assistant (2024)7.50