mlsanityData to 14 Oct 2026

Graph RAG-Tool Fusion

arXiv 2502.07223 ↗First posted 11 Feb 2025cs.CLcited by 15

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

also in 1 more
Abstract (arXiv)

Recent developments in retrieval-augmented generation (RAG) for selecting relevant tools from a tool knowledge base enable LLM agents to scale their complex tool calling capabilities to hundreds or thousands of external tools, APIs, or agents-as-tools. However, traditional RAG-based tool retrieval fails to capture structured dependencies between tools, limiting the retrieval accuracy of a retrieved tool's dependencies. For example, among a vector database of tools, a "get stock price" API requires a "stock ticker" parameter from a "get stock ticker" API, and both depend on OS-level internet connectivity tools. In this paper, we address this limitation by introducing Graph RAG-Tool Fusion, a novel plug-and-play approach that combines the strengths of vector-based retrieval with efficient graph traversal to capture all relevant tools (nodes) along with any nested dependencies (edges) within the predefined tool knowledge graph. We also present ToolLinkOS, a new tool selection benchmark of 573 fictional tools, spanning over 15 industries, each with an average of 6.3 tool dependencies. We demonstrate that Graph RAG-Tool Fusion achieves absolute improvements of 71.7% and 22.1% over na"ive RAG on ToolLinkOS and ToolSandbox benchmarks, respectively (mAP@10). ToolLinkOS dataset is available at https://github.com/EliasLumer/Graph-RAG-Tool-Fusion-ToolLinkOS

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 45 of its 53 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

45 of 53 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  2. 2024GRAG: Graph Retrieval-Augmented Generation26 May
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  4. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering12 Feb

Other references · 41

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  6. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  7. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  8. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  9. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  10. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  11. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  12. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
29 more
  1. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
  2. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  3. 2024Corrective Retrieval Augmented Generationcited by 197
  4. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  5. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 159
  6. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 154
  7. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 124
  8. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  9. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  10. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 90
  11. 2023Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPTcited by 80
  12. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  13. 2024Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmarkcited by 63
  14. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
  15. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59
  16. 2025ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenariocited by 55
  17. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 52
  18. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documentscited by 49
  19. 2023DiffKG: Knowledge Graph Diffusion Model for Recommendationcited by 41
  20. 2020Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approachcited by 32
  21. 2024Text2Cypher: Bridging Natural Language and Graph Databasescited by 30
  22. 2023A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databasescited by 25
  23. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  24. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  25. 2024Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chainscited by 20
  26. 2024REAPER: Reasoning based Retrieval Planning for Complex RAG Systemscited by 16
  27. 2023ProTIP: Progressive Tool Retrieval Improves Planningcited by 12
  28. 2024Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schemacited by 10
  29. 2024GraphER: A Structure-aware Text-to-Graph Model for Entity and Relation Extractioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 8.

15 papers.

Sort:

By area:

Similar, not cited

Close in wording, no citation either way

  1. 2026SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation
  2. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction
  3. 2026Atomic Information Flow: A Network Flow Model for Tool Attributions in RAG Systems
  4. 2026Reliable Graph-RAG for Codebases: AST-Derived Graphs vs LLM-Extracted Knowledge Graphs
  5. 2023Context Tuning for Retrieval Augmented Generation
  6. 2026Plan or Retrieve First? A Scale Study of Tool Discovery Architectures
  7. 2026Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data
  8. 2025Online-Optimized RAG for Tool Use and Function Calling