ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
This addresses tool selection efficiency for LLM agents, though it appears incremental as it builds on existing tool-use frameworks.
The paper tackles the problem of LLM agents struggling with redundant tools and context limits in tool selection, proposing ToolScope with merging and filtering components that achieved 8.38% to 38.6% accuracy gains on benchmarks.
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.