ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering

TL;DR

ToolScope improves LLM agent tool use by merging redundant tools and selecting relevant ones, boosting accuracy within context constraints.

Contribution

Introduces ToolScope, a system with auto-correction and retrieval modules, to reduce redundancy and improve tool relevance selection for LLMs.

Findings

Achieves 8.38% to 38.6% improvement in tool selection accuracy.

Effectively reduces toolset redundancy and manages context limits.

Demonstrates effectiveness across multiple LLMs and benchmarks.

Abstract

Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapping names and descriptions, introducing ambiguity and reducing selection accuracy. LLMs also face strict input context limits, preventing efficient consideration of large toolsets. To address these challenges, we propose ToolScope, which includes: (1) ToolScopeMerger with Auto-Correction to automatically audit and fix tool merges, reducing redundancy, and (2) ToolScopeRetriever to rank and select only the most relevant tools for each query, compressing toolsets to fit within context limits without sacrificing accuracy. Evaluations on three state-of-the-art LLMs and three open-source tool-use benchmarks show gains of 8.38% to 38.6% in tool selection accuracy, demonstrating ToolScope's effectiveness in enhancing LLM tool use.