mlsanityData to 7 Oct 2026

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

arXiv 2510.20036 ↗First posted 22 Oct 2025cs.CL cs.SEcited by 19

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

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.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 23 of its 49 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

23 of 49 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents9 May
  2. 2024Meta-Reasoning Improves Tool Use in Large Language Models7 Nov
  3. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases18 Oct
  4. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions10 Oct
  5. 2024Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark14 May
  6. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction11 Jan
  7. 2023From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting18 Dec
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  9. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases8 Jun
  10. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  11. 2023Gorilla: Large Language Model Connected with Massive APIs24 May

Other references · 12

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  3. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  4. 2025Survey on Evaluation of LLM-based Agentscited by 190
  5. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
  6. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  7. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 85
  8. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 69
  9. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 59
  10. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 50
  11. 2023MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Promptingcited by 27
  12. 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Modelcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 19.

19 papers.

Sort:

By area:

  1. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  2. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 11
  3. 2026ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agentscited by 9
  4. 2026Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agentscited by 5
  5. 2026ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agentscited by 5
  6. 2026Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agentscited by 4
  7. 2026From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agentscited by 3
  8. 2026The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Projectcited by 1
  9. 2026Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recoverycited by 1
  10. 2026HiSkill: Empowering LLM Agents with Hierarchical Skill Graphscited by 1
  11. 2026A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimizationcited by 0
  12. 2026When Does Restricting a Coding Agent to executecode Help? A Regime × Agent-Design Ablationcited by 0
7 more
  1. 2026ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memorycited by 0
  2. 2026Set-shifting Behavioral Test for Harnessed Agentscited by 0
  3. 2026Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utilitycited by 0
  4. 2026DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agentscited by 0
  5. 2026Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matchingcited by 0
  6. 2026AgentBetta: Verification-Driven Adaptive Configuration of an AI Nano-Agent through Selective Expansion and Verified Contractioncited by 0
  7. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction
  2. 2025ToolFuzz -- Automated Agent Tool Testing
  3. 2024LLM With Tools: A Survey
  4. 2026JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
  5. 2023ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
  6. 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents
  7. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
  8. 2025Tool Preferences in Agentic LLMs are Unreliable