SOURCE-LINKED INTELLIGENCE

Toollery: Scaling LLM Agents to Thousands of Skills and Tools

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

As LLM agents are exposed to hundreds to tens of thousands of skills, tools, and API functions, full-library prompting becomes costly, slow, and less reliable: each added candidate increases prompt tokens and latency, while longer candidate lists introduce more distractors for LLM selection. We present \textbf{Toollery}, a training-free candidate-compression framework for scalable LLM skill/tool selection. Following established document-side query expansion, Toollery generates user-intent queries from each skill/tool specification and builds a retrieval index that maps real user requests to co

Read original source ↗ Open in workspace

recordType

paper

region

Global