Dynamic Tool Dependency Retrieval for Efficient Function Calling
This addresses inefficiencies in on-device LLM agents by enhancing tool selection for complex tasks, though it is an incremental improvement over existing retrieval methods.
The paper tackled the problem of static tool retrieval in function-calling agents by proposing Dynamic Tool Dependency Retrieval (DTDR), which improved function-calling success rates by 23% to 104% compared to state-of-the-art static methods.
Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length. However, existing retrieval methods rely on static and limited inputs, failing to capture multi-step tool dependencies and evolving task context. This limitation often introduces irrelevant tools that mislead the agent, degrading efficiency and accuracy. We propose Dynamic Tool Dependency Retrieval (DTDR), a lightweight retrieval method that conditions on both the initial query and the evolving execution context. DTDR models tool dependencies from function calling demonstrations, enabling adaptive retrieval as plans unfold. We benchmark DTDR against state-of-the-art retrieval methods across multiple datasets and LLM backbones, evaluating retrieval precision, downstream task accuracy, and computational efficiency. Additionally, we explore strategies to integrate retrieved tools into prompts. Our results show that dynamic tool retrieval improves function calling success rates between $23\%$ and $104\%$ compared to state-of-the-art static retrievers.