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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Marianne Menglin, Garcia, Daniel, Parllaku, Fjona, Upadhyay, Vikas, Shah, Syed Fahad Allam, Roth, Dan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910202266124288
author Liu, Marianne Menglin
Garcia, Daniel
Parllaku, Fjona
Upadhyay, Vikas
Shah, Syed Fahad Allam
Roth, Dan
author_facet Liu, Marianne Menglin
Garcia, Daniel
Parllaku, Fjona
Upadhyay, Vikas
Shah, Syed Fahad Allam
Roth, Dan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20036
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
Liu, Marianne Menglin
Garcia, Daniel
Parllaku, Fjona
Upadhyay, Vikas
Shah, Syed Fahad Allam
Roth, Dan
Computation and Language
Software Engineering
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.
title ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
topic Computation and Language
Software Engineering
url https://arxiv.org/abs/2510.20036