Dynamic Tool Dependency Retrieval for Efficient Function Calling

Bhrij Patel, Davide Belli, Amir Jalalirad, Maximilian Arnold, Aleksandr Ermolov, Bence Major

Keywords: tool selection; tool dependency graphs; on-device agents; retrieval; in-context learning; efficiency; function calling

TL;DR: Query and history-conditioned retrieval of relevant tool dependencies for efficient function calling on-device using in-context learning

Abstract:

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.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 11191