mlsanityData to 14 Oct 2026

Top Ten Challenges Towards Agentic Neural Graph Databases

arXiv 2501.14224 ↗First posted 24 Jan 2025cs.AI cs.DB cs.LGcited by 13

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

Abstract (arXiv)

Graph databases (GDBs) like Neo4j and TigerGraph excel at handling interconnected data but lack advanced inference capabilities. Neural Graph Databases (NGDBs) address this by integrating Graph Neural Networks (GNNs) for predictive analysis and reasoning over incomplete or noisy data. However, NGDBs rely on predefined queries and lack autonomy and adaptability. This paper introduces Agentic Neural Graph Databases (Agentic NGDBs), which extend NGDBs with three core functionalities: autonomous query construction, neural query execution, and continuous learning. We identify ten key challenges in realizing Agentic NGDBs: semantic unit representation, abductive reasoning, scalable query execution, and integration with foundation models like large language models (LLMs). By addressing these challenges, Agentic NGDBs can enable intelligent, self-improving systems for modern data-driven applications, paving the way for adaptable and autonomous data management solutions.

Key facts. Cited by 13 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 45 of its 87 references that are in the map. First posted on arXiv 24 Jan 2025.

Builds on

45 of 87 references.

References · 45

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2017Deep Learning Scaling is Predictable, Empiricallycited by 582
  3. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  4. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 242
  5. 2020Information Leakage in Embedding Modelscited by 203
  6. 2020Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddingscited by 171
  7. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
  8. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 129
  9. 2018Embedding Logical Queries on Knowledge Graphscited by 120
  10. 2019ASER: A Large-scale Eventuality Knowledge Graphcited by 89
  11. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  12. 2019Reasoning Over Semantic-Level Graph for Fact Checkingcited by 69
33 more
  1. 2023Survey of Vector Database Management Systemscited by 39
  2. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  3. 2024Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defensescited by 30
  4. 2022Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimizationcited by 29
  5. 2023Logical Message Passing Networks with One-hop Inference on Atomic Formulascited by 28
  6. 2017KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Featurescited by 26
  7. 2022FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discoverycited by 23
  8. 2024Optimizing LLM Queries in Relational Data Analytics Workloadscited by 22
  9. 2021Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphscited by 21
  10. 2023Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraintscited by 21
  11. 2024Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspectivecited by 20
  12. 2023Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generationcited by 19
  13. 2022Manu: A Cloud Native Vector Database Management Systemcited by 18
  14. 2019Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerabilitycited by 17
  15. 2021SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphscited by 17
  16. 2023Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transportcited by 16
  17. 2017G-CORE: A Core for Future Graph Query Languagescited by 13
  18. 2023Sequential Query Encoding For Complex Query Answering on Knowledge Graphscited by 13
  19. 2022Neural Graph Databasescited by 11
  20. 2022NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge Graphscited by 9
  21. 2024EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphscited by 9
  22. 2022The World of Graph Databases from An Industry Perspectivecited by 7
  23. 2023Understanding Inter-Session Intentions via Complex Logical Reasoningcited by 7
  24. 2019TigerGraph: A Native MPP Graph Databasecited by 6
  25. 2023LitCQD: Multi-Hop Reasoning in Incomplete Knowledge Graphs with Numeric Literalscited by 6
  26. 2024Intention Knowledge Graph Construction for User Intention Relation Modelingcited by 6
  27. 2023Knowledge Graphs Queryingcited by 5
  28. 2023Privacy-Preserved Neural Graph Databasescited by 5
  29. 2024A Survey of Distributed Graph Algorithms on Massive Graphscited by 5
  30. 2024NeurDB: On the Design and Implementation of an AI-powered Autonomous Databasecited by 5
  31. 2023Independent Distribution Regularization for Private Graph Embeddingcited by 4
  32. 2023Cost-Intelligent Data Analytics in the Cloudcited by 2
  33. 2024Meta Operator for Complex Query Answering on Knowledge Graphscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

Similar, not cited

Close in wording, no citation either way

  1. 2025GDS Agent for Graph Algorithmic Reasoning
  2. 2024GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
  3. 2024Towards Evaluating Large Language Models for Graph Query Generation
  4. 2026Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines
  5. 2024NAT-NL2GQL: A Novel Multi-Agent Framework for Translating Natural Language to Graph Query Language
  6. 2026From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvement
  7. 2023Graph Agent: Explicit Reasoning Agent for Graphs
  8. 2026GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning