Dynamic Tool Dependency Retrieval for Lightweight Function Calling

ArXi:2512.17052v4 Announce Type: replace 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