mlsanityData to 14 Oct 2026

Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve

arXiv 2610.18616 ↗First posted 13 Oct 2026cs.CL cs.AI cs.IRcited by 0

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

Abstract (arXiv)

Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidence agents can access, even when they write code to combine tool calls or process retrieved subgraphs. We propose direct knowledge graph interaction (DKGI), a harness in which language model agents create graph access tools directly over complete node and edge files. The agent writes Python code to follow relations, combine node sets, and select textual evidence, interleaving execution with shell search and file inspection. This lets agents process large node sets in bulk while returning selected text for the model to assess. Execution feedback guides tool creation and revision, while the evolving tools determine what evidence the agent gathers next. On benchmark datasets spanning three domains, training-free DKGI exceeds the strongest published baseline by at least 6.7 Hit@1 points on every graph, even with a minimal harness. Controlled ablations show the benefits of multi-turn programming over shell-only access and predefined graph tools, while trajectories show agents revising code to extend searches or address errors. These findings highlight the value of allowing tool creation and tool use to co-evolve during graph search. Our code and data are available at https://github.com/leopoldwhite/DKGI.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 41 of its 79 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

41 of 79 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026Schema-Agnostic Graph Reasoning Agent for Hybrid Knowledge Graphs16 Aug
  2. 2026Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion12 Jun
  3. 2026Is Grep All You Need? How Agent Harnesses Reshape Agentic Search14 May
  4. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction3 May
  5. 2025PASemiQA: Plan-Assisted Agent for Question Answering on Semi-Structured Data with Text and Relational Information28 Feb
  6. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph17 Feb

Other references · 35

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  3. 2023Teaching Large Language Models to Self-Debugcited by 988
  4. 2015Image-based Recommendations on Styles and Substitutescited by 706
  5. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  6. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  7. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  8. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  9. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  10. 2023Large Language Models as Tool Makerscited by 303
  11. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  12. 2024Generative Representational Instruction Tuningcited by 233
23 more
  1. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 171
  2. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 129
  3. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  4. 2016Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervisioncited by 103
  5. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graphcited by 103
  6. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 95
  7. 2025PyVision: Agentic Vision with Dynamic Toolingcited by 79
  8. 2020KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Basecited by 78
  9. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 78
  10. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 75
  11. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 72
  12. 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Basescited by 55
  13. 2015Addressing Complex and Subjective Product-Related Queries with Customer Reviewscited by 29
  14. 2024HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Basescited by 29
  15. 2024Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrievalcited by 26
  16. 2024CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Eracited by 16
  17. 2025Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basescited by 11
  18. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databasescited by 7
  19. 2026GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Basescited by 7
  20. 2025Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inferencecited by 5
  21. 2025Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledgecited by 3
  22. 2026Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrievalcited by 3
  23. 2026Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
  2. 2026Agents-K1: Towards Agent-native Knowledge Orchestration
  3. 2026GraphWalk: Enabling Reasoning in Large Language Models through Tool-Based Graph Navigation
  4. 2026GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
  5. 2026Extracting Knowledge from Tools in LLM Agents
  6. 2026Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement
  7. 2025Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning
  8. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval