mlsanityData to 14 Oct 2026

Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems

arXiv 2511.01854 ↗First posted 3 Nov 2025cs.CLcited by 15

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

Abstract (arXiv)

Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. However, existing retrieval methods typically match queries against coarse agent-level descriptions before routing, which obscures fine-grained tool functionality and often results in suboptimal agent selection. We introduce Tool-to-Agent Retrieval, a unified framework that embeds both tools and their parent agents in a shared vector space and connects them through metadata relationships. By explicitly representing tool capabilities and traversing metadata to the agent level, Tool-to-Agent Retrieval enables granular tool-level or agent-level retrieval, ensuring that agents and their underlying tools or MCP servers are equally represented without the context dilution that arises from chunking many tools together. Evaluating Tool-to-Agent Retrieval across eight embedding models, our approach achieves consistent improvements of 19.4% in Recall@5 and 17.7% in nDCG@5 over previous state-of-the-art agent retrievers on the LiveMCPBench benchmark.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 30 of its 36 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

30 of 36 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?3 Aug
  2. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations29 Jul
  3. 2025MCP-Zero: Active Tool Discovery for Autonomous LLM Agents1 Jun
  4. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents9 May
  5. 2025ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario17 Jan
  6. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases18 Oct
  7. 2024Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark14 May
  8. 2024Planning and Editing What You Retrieve for Enhanced Tool Learning30 Mar
  9. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls6 Feb
  10. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use4 Oct
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  12. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs14 Apr

Other references · 18

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  3. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  4. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  5. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  6. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  7. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  8. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  9. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 129
  10. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  11. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  12. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
6 more
  1. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59
  2. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 52
  3. 2024ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrievalcited by 41
  4. 2020Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approachcited by 32
  5. 2024REAPER: Reasoning based Retrieval Planning for Complex RAG Systemscited by 16
  6. 2023ProTIP: Progressive Tool Retrieval Improves Planningcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 12.

15 papers.

Sort:

By area:

  1. 2026Code as Agent Harnesscited by 47
  2. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  3. 2026Think like a Scientist: Physics-guided LLM Agent for Equation Discoverycited by 16
  4. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 14
  5. 2026Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agentscited by 12
  6. 2025Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systemscited by 5
  7. 2025Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systemscited by 4
  8. 2026Automated Interpretability and Feature Discovery in Language Models with Agentscited by 4
  9. 2026Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?cited by 4
  10. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Modelscited by 2
  11. 2026GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexingcited by 2
  12. 2026Skill Description Deception Attack against Task Routing in Internet of Agentscited by 2
3 more
  1. 2026Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQLcited by 0
  2. 2026A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimizationcited by 0
  3. 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. 2025GRETEL: A Goal-driven Retrieval and Execution-based Trial Framework for LLM Tool Selection Enhancing
  3. 2026SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents
  4. 2026Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning
  5. 2026ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory
  6. 2026LLM Agents Factory: Retrieval of Domain-Specific LLM Agents
  7. 2026UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
  8. 2025AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol