mlsanityData to 14 Oct 2026

Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systems

arXiv 2511.18194 ↗First posted 22 Nov 2025cs.CLcited by 4

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools. However, existing agent, MCP, and retrieval methods typically match queries against a single agent description, obscuring fine-grained tool capabilities of each agent, resulting in suboptimal agent selection. We introduce Agent-as-a-Graph retrieval, a knowledge graph retrieval augmented generation approach that represents both tools and their parent agents as nodes and edges in a knowledge graph. During retrieval, i) relevant agents and tool nodes are first retrieved through vector search, ii) we apply a type-specific weighted reciprocal rank fusion (wRRF) for reranking tools and agents, and iii) parent agents are traversed in the knowledge graph for the final set of agents. We evaluate Agent-as-a-Graph on the LiveMCPBenchmark, achieving 14.9% and 14.6% improvements in Recall@5 and nDCG@5 over prior state-of-the-art retrievers, and 2.4% improvements in wRRF optimizations.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 32 of its 41 references that are in the map. First posted on arXiv 22 Nov 2025.

Builds on

32 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents19 Apr

Other references · 31

  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  5. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  6. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  7. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  8. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  9. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  10. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
  11. 2024Corrective Retrieval Augmented Generationcited by 197
  12. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 154
19 more
  1. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 124
  2. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  3. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  4. 2023Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPTcited by 80
  5. 2024GRAG: Graph Retrieval-Augmented Generationcited by 78
  6. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
  7. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59
  8. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 52
  9. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agentscited by 36
  10. 2025MCP-Zero: Active Tool Discovery for Autonomous LLM Agentscited by 33
  11. 2020Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approachcited by 32
  12. 2024Text2Cypher: Bridging Natural Language and Graph Databasescited by 30
  13. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  14. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  15. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  16. 2025Graph RAG-Tool Fusioncited by 15
  17. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  18. 2023ProTIP: Progressive Tool Retrieval Improves Planningcited by 12
  19. 2024Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schemacited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  2. 2026SchemaRouter: Field-Aware Tool Routing for Efficient Heterogeneous Agentic RAGcited by 2
  3. 2026Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answeringcited by 1
  4. 2026Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Open-World Retrieval-Augmented Generation on Knowledge Graph: A Multi-Agent Collaboration Framework
  2. 2025Path-Constrained Retrieval: A Structural Approach to Reliable LLM Agent Reasoning Through Graph-Scoped Semantic Search
  3. 2026MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
  4. 2026EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval
  5. 2026LLM Agents Factory: Retrieval of Domain-Specific LLM Agents
  6. 2026GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
  7. 2025Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
  8. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval