pith. sign in

arxiv: 2606.11560 · v1 · pith:BSZ52SLWnew · submitted 2026-06-10 · 💻 cs.DB · cs.AI

LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems

Arijit Khan , Longxu Sun , Xin Huang This is my paper

Pith reviewed 2026-06-27 07:59 UTC · model grok-4.3

classification 💻 cs.DB cs.AI
keywords large language modelsgraphsknowledge graphsAI agentsgraph neural networksgraph machine learningdata managementsynergistic systems
0
0 comments X

The pith

Large language models and graph structures converge through three synergies to overcome limitations in structured reasoning.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sets out to show that LLMs alone fall short on multi-hop and structured tasks, so they must combine with graph data to produce more grounded results. It describes three synergies that are taking shape: graphs supplying computation for LLM retrieval and reasoning, LLMs and knowledge graphs supporting each other in construction and consistency checks, and graph algorithms strengthening AI agents in planning and multi-step work. The same models also open natural-language routes into graph data management and hybrid learning pipelines. A reader would care because these links point toward AI that can handle both free text and relational data across social, biological, financial, and web settings without separate tool chains.

Core claim

Three complementary synergies are emerging between LLMs and graphs. LLMs gain retrieval and reasoning power when augmented by graph computation. LLMs and knowledge graphs integrate in both directions, with LLMs helping build and curate the graphs while the graphs enforce semantic and factual constraints on the models. Graph algorithms in turn strengthen AI agents for planning, decision making, and multi-step reasoning. At the same time LLMs supply natural language interfaces and hybrid pipelines that advance graph data management and graph machine learning. The tutorial brings the algorithms, systems, and design principles of these directions into one framework for next-generation graph-nati

What carries the argument

The three complementary synergies between LLMs and graph-structured data, plus LLMs' new capabilities for graph data management and hybrid GNN pipelines.

If this is right

  • LLMs perform more reliable multi-hop inference when graph computation handles retrieval and structure.
  • Knowledge graphs maintain higher factual consistency once LLMs assist in their construction and curation.
  • AI agents achieve stronger planning and multi-step reasoning when graph algorithms guide their decisions.
  • Graph data management and machine learning become accessible through natural language interfaces supplied by LLMs.
  • Hybrid LLM-GNN pipelines open new routes for graph machine learning tasks.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The framing may encourage data-management researchers to treat LLM-graph hybrids as a single design space rather than separate toolkits.
  • Future work could test whether systems that combine all three synergies outperform those using only one or two on cross-domain tasks.
  • The same pattern of mutual support might apply to other structured data types if similar complementary strengths appear.

Load-bearing premise

The three listed synergies are genuinely complementary and already emerging at a scale that justifies a single unified tutorial framework.

What would settle it

Benchmarks in which adding any one graph component to LLMs produces no measurable gain in reasoning accuracy or factual consistency across the domains listed in the abstract.

read the original abstract

Large Language Models (LLMs) have advanced rapidly, but their limitations in structured and multi-hop reasoning underscore the need for graph-native, synergistic artificial intelligence (AI) systems. Graph-structured data underpins critical applications across social, biological, financial, transportation, web, and knowledge domains, making it essential to understand how LLMs can leverage graph computation for grounded, context-rich inference. Three complementary synergies are emerging: LLMs augmented with graph computation for retrieval and reasoning; bidirectional integration between LLMs and knowledge graphs (KGs), where LLMs support KG construction and curation while KGs enforce semantic constraints and factual consistency; and AI agents strengthened by graph algorithms for planning, decision making, and multi-step reasoning. In parallel, LLMs introduce new capabilities for graph data management and graph machine learning (ML) through natural language interfaces and hybrid LLM-graph neural network (GNN) pipelines. This tutorial synthesizes the algorithms, systems, and design principles driving these converging directions, offering data science and data mining researchers a unified perspective on integrating LLMs, graph data management, graph mining, graph ML, and agentic computation into next-generation graph-native AI systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript is a tutorial synthesizing the integration of Large Language Models (LLMs) with graph-structured data and computation. It identifies three emerging complementary synergies—LLMs augmented by graph computation for retrieval/reasoning, bidirectional LLM-KG integration for construction/curation and consistency enforcement, and graph algorithms strengthening AI agents for planning and multi-step reasoning—while also covering LLMs' contributions to graph data management and hybrid LLM-GNN pipelines. The work aims to provide data science and data mining researchers with a unified perspective on algorithms, systems, and design principles for graph-native AI systems.

Significance. If the synthesis is accurate and comprehensive, the tutorial could offer a useful organizing framework for an active intersection of LLMs, graph data management, graph mining, and agentic systems, helping researchers navigate converging research directions. As a descriptive survey without new derivations, datasets, or experiments, its primary value lies in literature synthesis and design principles rather than novel technical results.

minor comments (2)
  1. [Abstract] Abstract: the claim that the three synergies are 'complementary' and 'emerging' at a scale justifying a unified tutorial would benefit from explicit criteria or literature volume indicators in the introduction to substantiate the framing.
  2. [Introduction] The manuscript positions itself as a tutorial for data science and data mining researchers, but the abstract does not indicate the scope of covered papers or selection methodology; adding this in §1 or a dedicated related-work section would improve reproducibility of the synthesis.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary, recognition of the tutorial's potential utility as an organizing framework, and recommendation for minor revision. No specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity: survey framing is descriptive

full rationale

The document is a tutorial/survey paper whose central claim is an organizing premise that three synergies between LLMs and graphs are emerging and complementary. No mathematical derivations, equations, fitted parameters, or predictions appear in the abstract or stated scope. The claim is presented as a synthesis of existing algorithms and design principles rather than a result derived from inputs internal to the paper. No self-citation load-bearing steps, self-definitional reductions, or ansatz smuggling are present. The paper is therefore self-contained against external benchmarks with a circularity burden of zero.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey paper the work rests on standard domain assumptions in AI and graph theory (e.g., that graphs are a useful representation for relational data and that LLMs can interface with external tools) but introduces no new free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5735 in / 1082 out tokens · 15401 ms · 2026-06-27T07:59:13.983021+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

84 extracted references · 2 linked inside Pith

  1. [1]

    In: ICSC (2024)

    Avila, C.V.S., Vidal, V.M.P., Franco, W., Casanova, M.A.: Experiments with Text- to-SPARQL based on ChatGPT. In: ICSC (2024)

    2024

  2. [2]

    In: MATCHING (2023)

    Baek, J., Aji, A.F., Saffari, A.: Knowledge-augmented language model prompting for zero-shot knowledge graph question answering. In: MATCHING (2023)

    2023

  3. [3]

    CoRRabs/2506.18019(2025)

    Bei, Y., Zhang, W., Wang, S., Chen, W., Zhou, S., Chen, H., Li, Y., Bu, J., Pan, S., Yu, Y., King, I., Karray, F., Yu, P.S.: Graphs meet AI agents: Taxonomy, progress, and future opportunities. CoRRabs/2506.18019(2025)

    arXiv 2025

  4. [4]

    In: AAAI (2024)

    Besta, M., Blach, N., Kubicek, A., Gerstenberger, R., Podstawski, M., Gianinazzi, L., Gajda, J., Lehmann, T., Niewiadomski, H., Nyczyk, P., Hoefler, T.: Graph of thoughts: Solving elaborate problems with large language models. In: AAAI (2024)

    2024

  5. [5]

    CoRR abs/2502.14902(2025)

    Chen, B., Guo, Z., Yang, Z., Chen, Y., Chen, J., Liu, Z., Shi, C., Yang, C.: Pathrag: Pruning graph-based retrieval augmented generation with relational paths. CoRR abs/2502.14902(2025)

    arXiv 2025

  6. [6]

    In: KDD (2024)

    Chen, N., Li, Y., Tang, J., Li, J.: Graphwiz: An instruction-following language model for graph computational problems. In: KDD (2024)

    2024

  7. [7]

    CoRR abs/2412.05547(2024)

    Chen, W., Bai, T., Su, J., Luan, J., Liu, W., Shi, C.: Kg-retriever: Effi- cient knowledge indexing for retrieval-augmented large language models. CoRR abs/2412.05547(2024)

    arXiv 2024

  8. [8]

    SIGMOD Rec.51(1), 33–40 (2022)

    Deng, X., Sun, H., Lees, A., Wu, Y., Yu, C.: Turl: Table understanding through representation learning. SIGMOD Rec.51(1), 33–40 (2022)

    2022

  9. [9]

    CoRRabs/2404.16130(2024)

    Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., Larson, J.: From local to global: A graph rag approach to query-focused summarization. CoRRabs/2404.16130(2024)

    Pith/arXiv arXiv 2024

  10. [10]

    KDD Tutorial (2024)

    Fan, W., Ding, Y., Wang, S., Ning, L., Li, H., Yin, D., Chua, T.S., Li, Q.: Rag meets llms: Towards retrieval-augmented large language models. KDD Tutorial (2024)

    2024

  11. [11]

    Fernandez, R.C., Elmore, A.J., Franklin, M.J., Krishnan, S., Tan, C.: How large languagemodelswilldisruptdatamanagement.Proc.VLDBEndow.16(11),3302– 3309 (2023)

    2023

  12. [12]

    Gallici, M., Martin, M., Masmitja, I.: Transfqmix: Transformers for leveraging the graphstructureofmulti-agentreinforcementlearningproblems.In:AAMAS(2023)

    2023

  13. [13]

    In: IJCAI (2024)

    Ganesan, B., Ghosh, S., Gupta, N., Kesarwani, M., Mehta, S., Sindhgatta, R.: Llm-powered graphql generator for data retrieval. In: IJCAI (2024)

    2024

  14. [14]

    In: AAAI

    Guan, X., Liu, Y., Lin, H., Lu, Y., He, B., Han, X., Sun, L.: Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting. In: AAAI. pp. 18126–18134 (2024)

    2024

  15. [15]

    CoRRabs/2511.08274(2025)

    Gusarov, A., Volkova, A., Khrulkov, V., Kuznetsov, A., Maslov, E., Oseledets, I.V.: Multi-agent graphrag: A text-to-cypher framework for labeled property graphs. CoRRabs/2511.08274(2025)

    arXiv 2025

  16. [16]

    In: NeurIPS (2024)

    Gutierrez,B.J.,Shu,Y.,Gu,Y.,Yasunaga,M.,Su,Y.:Hipporag:Neurobiologically inspired long-term memory for large language models. In: NeurIPS (2024)

    2024

  17. [17]

    VLDB Endow.16(12), 4114–4115 (2023)

    Halevy,A.Y.,Choi,Y.,Floratou,A.,Franklin,M.J.,Noy,N.F.,Wang,H.:Willllms reshape, supercharge, or kill data science? Proc. VLDB Endow.16(12), 4114–4115 (2023)

    2023

  18. [18]

    CoRRabs/2410.05130(2024)

    Hu, Y., Lei, R., Huang, X., Wei, Z., Liu, Y.: Scalable and accurate graph reasoning with llm-based multi-agents. CoRRabs/2410.05130(2024)

    arXiv 2024

  19. [19]

    CoRRabs/2405.16506(2024) LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems 7

    Hu, Y., Lei, Z., Zhang, Z., Pan, B., Ling, C., Zhao, L.: GRAG: Graph retrieval- augmented generation. CoRRabs/2405.16506(2024) LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems 7

    arXiv 2024

  20. [20]

    Huang, C., Ren, X., Tang, J., Yin, D., Chawla, N.V.: Large language models for graphs: Progresses and directions. In: WWW. pp. 1284–1287 (2024)

    2024

  21. [21]

    CoRRabs/2206.13163(2022)

    Huang, N., Deshpande, Y.R., Liu, Y., Alberts, H., Cho, K., Vania, C., Calixto, I.: Endowing language models with multimodal knowledge graph representations. CoRRabs/2206.13163(2022)

    arXiv 2022

  22. [22]

    Huang, X., Han, K., Yang, Y., Bao, D., Tao, Q., Chai, Z., Zhu, Q.: Can gnn be good adapter for llms? In: WWW (2024)

    2024

  23. [23]

    CoRRabs/2312.11282(2023)

    Huang, Y.: Evaluating and enhancing large language models for conversational reasoning on knowledge graphs. CoRRabs/2312.11282(2023)

    arXiv 2023

  24. [24]

    In: ACL (2025)

    Jiang, J., Zhou, K., Zhao, X., Song, Y., Zhu, C., Zhu, H., Wen, J.: Kg-agent: An efficient autonomous agent framework for complex reasoning over knowledge graph. In: ACL (2025)

    2025

  25. [25]

    IEEE Trans

    Jin, B., Liu, G., Han, C., Jiang, M., Ji, H., Han, J.: Large language models on graphs: A comprehensive survey. IEEE Trans. Knowl. Data Eng.36(12), 8622– 8642 (2024)

    2024

  26. [26]

    CoRR abs/2310.10196(2023)

    Jin, M., Wen, Q., Liang, Y., Zhang, C., Xue, S., Wang, X., Zhang, J., Wang, Y., Chen, H., Li, X., Pan, S., Tseng, V.S., Zheng, Y., Chen, L., Xiong, H.: Large models for time series and spatio-temporal data: A survey and outlook. CoRR abs/2310.10196(2023)

    Pith/arXiv arXiv 2023

  27. [27]

    In: EMNLP-IJCNLP (2019)

    Joshi, M., Levy, O., Zettlemoyer, L., Weld, D.S.: Bert for coreference resolution: Baselines and analysis. In: EMNLP-IJCNLP (2019)

    2019

  28. [28]

    In: EMNLP

    Ko,S.,Cho,H.,Chae,H.,Yeo,J.,Lee,D.:Evidence-focusedfactsummarizationfor knowledge-augmented zero-shot question answering. In: EMNLP. pp. 10636–10651 (2024)

    2024

  29. [29]

    In: ACML

    Leurent, E., Maillard, O.: Monte-carlo graph search: the value of merging similar states. In: ACML. PMLR, vol. 129, pp. 577–592 (2020)

    2020

  30. [30]

    Future Internet16(1) (2024)

    Li, X., Henriksson, A., Duneld, M., Nouri, J., Wu, Y.: Evaluating embeddings from pre-trained language models and knowledge graphs for educational content recommendation. Future Internet16(1) (2024)

    2024

  31. [31]

    In: IJCAI

    Li, Y., Li, Z., Wang, P., Li, J., Sun, X., Cheng, H., Yu, J.X.: A survey of graph meets large language model: Progress and future directions. In: IJCAI. pp. 8123– 8131 (2024)

    2024

  32. [32]

    arXivabs/2406.01145(2024)

    Liu, G., Zhang, Y., Li, Y., Yao, Q.: Explore then determine: A GNN-LLM synergy framework for reasoning over knowledge graph. arXivabs/2406.01145(2024)

    arXiv 2024

  33. [33]

    In: ICLR (2024)

    Liu, H., Feng, J., Kong, L., Liang, N., Tao, D., Chen, Y., Zhang, M.: One for all: Towards training one graph model for all classification tasks. In: ICLR (2024)

    2024

  34. [34]

    IEEE Trans

    Liu, J., Yang, C., Lu, Z., Chen, J., Li, Y., Zhang, M., Bai, T., Fang, Y., Sun, L., Yu, P.S., Shi, C.: Graph foundation models: Concepts, opportunities and challenges. IEEE Trans. Pattern Anal. Mach. Intell.47(6), 5023–5044 (2025)

    2025

  35. [35]

    Liu, L., Wang, Z., Bai, J., Song, Y., Tong, H.: New frontiers of knowledge graph reasoning: Recent advances and future trends. In: WWW. pp. 1294–1297 (2024)

    2024

  36. [36]

    In: AAAI (2020)

    Liu, W., Zhou, P., Zhao, Z., Wang, Z., Ju, Q., Deng, H., Wang, P.: K-bert: Enabling language representation with knowledge graph. In: AAAI (2020)

    2020

  37. [37]

    CoRRabs/2403.00839(2024)

    Liu, X., Peng, Z., Yi, X., Xie, X., Xiang, L., Liu, Y., Xu, D.: Toolnet: Connecting llms with massive tools via tool graph. CoRRabs/2403.00839(2024)

    arXiv 2024

  38. [38]

    In: SGDA Workshop@VLDB (2024)

    Liu, Y., Wang, X., Ge, J., Wang, H., Xu, D., Jia, Y.: Text to graph query using filter condition attributes. In: SGDA Workshop@VLDB (2024)

    2024

  39. [39]

    arXiv:2410.13080 (2024) 8 Arijit Khan, Longxu Sun, and Xin Huang

    Luo, L., Zhao, Z., Gong, C., Haffari, G., Pan, S.: Graph-constrained rea- soning: Faithful reasoning on knowledge graphs with large language models. arXiv:2410.13080 (2024) 8 Arijit Khan, Longxu Sun, and Xin Huang

    arXiv 2024

  40. [40]

    In: SIGMOD (2026)

    Luo, Y., Li, G., Fan, J., Tang, N.: Data agents: Levels, state of the art, and open problems. In: SIGMOD (2026)

    2026

  41. [41]

    In: EDBT

    Ma, C., Chen, Y., Wu, T., Khan, A., Wang, H.: Unifying large language models and knowledge graphs for question answering: Recent advances and opportunities. In: EDBT. pp. 1174–1177 (2025)

    2025

  42. [42]

    CoRRabs/2501.08686(2025)

    Ma, C., Chakrabarti, S., Khan, A., Molnár, B.: Knowledge graph-based retrieval- augmented generation for schema matching. CoRRabs/2501.08686(2025)

    arXiv 2025

  43. [43]

    Ma, C., Chen, Y., Wu, T., Khan, A., Wang, H.: Large language models meet knowledgegraphsforquestionanswering:Synthesisandopportunities.In:EMNLP. pp. 24578–24597 (2025)

    2025

  44. [44]

    CoRRabs/2602.05708(2026)

    Ma, C., Zhang, Z., Khan, A., Schelter, S., Groth, P.: Cost-efficient rag for entity matching with llms: A blocking-based exploration. CoRRabs/2602.05708(2026)

    arXiv 2026

  45. [45]

    neo4j: neo4j.https://neo4j.com/labs/neodash/2.4/user-guide/extensions/ natural-language-queries/(2024)

    2024

  46. [46]

    In: NeurIPS (2024)

    Ning, Y., Liu, H.: Urbankgent: A unified large language model agent framework for urban knowledge graph construction. In: NeurIPS (2024)

    2024

  47. [47]

    IEEE Trans

    Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: A roadmap. IEEE Trans. Knowl. Data Eng.36(7), 3580–3599 (2024)

    2024

  48. [48]

    CoRR abs/2507.16971(2025)

    Perevalov, A., Both, A.: Text-to-sparql goes beyond english: Multilingual ques- tion answering over knowledge graphs through human-inspired reasoning. CoRR abs/2507.16971(2025)

    arXiv 2025

  49. [49]

    In: CIKM (2023)

    Regino, A.G., Caus, R.O., Hochgreb, V., dos Reis, J.C.: From natural language texts to rdf triples: A novel approach to generating e-commerce knowledge graphs. In: CIKM (2023)

    2023

  50. [50]

    Ren, X., Tang, J., Yin, D., Chawla, N.V., Huang, C.: A survey of large language models for graphs. In: KDD. pp. 6616–6626 (2024)

    2024

  51. [51]

    In: KONVENS

    Salnikov, M., Lysyuk, M., Braslavski, P., Razzhigaev, A., Malykh, V.A., Panchenko, A.: Answer candidate type selection: Text-to-text language model for closed book question answering meets knowledge graphs. In: KONVENS. pp. 155– 164 (2023)

    2023

  52. [52]

    In: ACL (2022)

    Saxena, A., Kochsiek, A., Gemulla, R.: Sequence-to-sequence knowledge graph completion and question answering. In: ACL (2022)

    2022

  53. [53]

    IEEE Trans

    Shang, W., Huang, X.: A survey of large language models on generative graph an- alytics: Query, learning, and applications. IEEE Trans. Knowl. Data Eng.37(12), 6799–6819 (2025)

    2025

  54. [54]

    CoRR abs/2508.20637(2025)

    Shi, B., Panagiotas, I.: GDS agent: A graph algorithmic reasoning agent. CoRR abs/2508.20637(2025)

    arXiv 2025

  55. [55]

    In: ICLR (2024)

    Sun, J., Xu, C., Tang, L., Wang, S., Lin, C., Gong, Y., Ni, L., Shum, H.Y., Guo, J.: Think-on-Graph: Deep and responsible reasoning of large language model with knowledge graph. In: ICLR (2024)

    2024

  56. [56]

    Sun, L., Tao, Z., Li, Y., Arakawa, H.: ODA: Observation-driven agent for integrat- ing LLMs and knowledge graphs. In: ACL. pp. 7417–7431 (2024)

    2024

  57. [57]

    Sung, M., Lee, J., Yi, S.S., Jeon, M., Kim, S., Kang, J.: Can language models be biomedical knowledge bases? In: EMNLP (2021)

    2021

  58. [58]

    Bull.47(2), 5–11 (2023)

    Tan, W.: Unstructured and structured data: Can we have the best of both worlds with large language models? IEEE Data Eng. Bull.47(2), 5–11 (2023)

    2023

  59. [59]

    Tian, S., Luo, Y., Xu, T., Yuan, C., Jiang, H., Wei, C., Wang, X.: KG-Adapter: Enablingknowledgegraphintegrationinlargelanguagemodelsthroughparameter- efficient fine-tuning. In: ACL. pp. 3813–3828 (2024) LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems 9

    2024

  60. [60]

    In: Table Representation Learning Workshop@NeurIPS (2022)

    Vogel, L., Hilprecht, B., Binnig, C.: Towards foundation models for relational databases [vision paper]. In: Table Representation Learning Workshop@NeurIPS (2022)

    2022

  61. [61]

    In: EMNLP-IJCNLP (2019)

    Wadden, D., Wennberg, U., Luan, Y., Hajishirzi, H.: Entity, relation, and event extraction with contextualized span representations. In: EMNLP-IJCNLP (2019)

    2019

  62. [62]

    In: EMNLP

    Wang, F., Bao, R., Wang, S., Yu, W., Liu, Y., Cheng, W., Chen, H.: Infuserki: En- hancinglargelanguagemodelswithknowledgegraphsviainfuser-guidedknowledge integration. In: EMNLP. pp. 3675–3688 (2024)

    2024

  63. [63]

    In: EMNLP

    Wang, J., Chen, M., Hu, B., Yang, D., Liu, Z., Shen, Y., Wei, P., Zhang, Z., Gu, J., Zhou, J., Pan, J.Z., Zhang, W., Chen, H.: Learning to plan for retrieval-augmented large language models from knowledge graphs. In: EMNLP. pp. 7813–7835 (2024)

    2024

  64. [64]

    In: ACL (1)

    Wang, S., Fan, W., Feng, Y., Lin, S., Ma, X., Wang, S., Yin, D.: Knowledge graph retrieval-augmented generation for llm-based recommendation. In: ACL (1). pp. 27152–27168. ACL (2025)

    2025

  65. [65]

    In: AAAI (2026)

    Wang, S., Fang, Y., Zhou, Y., Liu, X., Ma, Y.: Archrag: Attributed community- based hierarchical retrieval-augmented generation. In: AAAI (2026)

    2026

  66. [66]

    Wang, X., Gao, T., Zhu, Z., Zhang, Z., Liu, Z., Li, J., Tang, J.: Kepler: A unified model for knowledge embedding and pre-trained language representation. Trans. Assoc. Comput. Linguistics9, 176–194 (2021)

    2021

  67. [67]

    arXiv:2505.15116 (2025)

    Wang, Z., Liu, Z., Ma, T., Li, J., Zhang, Z., Fu, X., Li, Y., Yuan, Z., Song, W., Ma, Y., Zeng, Q., Chen, X., Zhao, J., Li, J., Jiang, M., Lio, P., Chawla, N.V., Zhang, C., Ye, Y.: Graph foundation models: A comprehensive survey. arXiv:2505.15116 (2025)

    arXiv 2025

  68. [68]

    Wang, Z., Zhang, C., Li, J., Chawla, N.V., Ye, Y.: Graph foundation models: Challenges, methods, and open questions. In: KDD. pp. 6184–6194 (2025)

    2025

  69. [69]

    In: ACL (2024)

    Wen, Y., Wang, Z., Sun, J.: Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models. In: ACL (2024)

    2024

  70. [70]

    Wu, X., Shen, Y., Shan, C., Song, K., Wang, S., Zhang, B., Feng, J., Cheng, H., Chen, W., Xiong, Y., Li, D.: Can graph learning improve planning in llm-based agents? In: NeurIPS (2024)

    2024

  71. [71]

    In: IJCKG (2023)

    Wu, Y., Hu, N., Bi, S., Qi, G., Ren, J., Xie, A., Song, W.: Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering. In: IJCKG (2023)

    2023

  72. [72]

    Xiong,G.,Bao,J.,Zhao,W.:Interactive-KBQA:Multi-turninteractionsforknowl- edge base question answering with large language models. In: ACL. pp. 10561– 10582 (2024)

    2024

  73. [73]

    In: BioNLP Workshop@ACL

    Yang, R., Liu, H., Marrese-Taylor, E., Zeng, Q., Ke, Y., Li, W., Cheng, L., Chen, Q., Caverlee, J., Matsuo, Y., Li, I.: KG-Rank: Enhancing large language mod- els for medical QA with knowledge graphs and ranking techniques. In: BioNLP Workshop@ACL. pp. 155–166 (2024)

    2024

  74. [74]

    CoRR abs/1909.03193(2019)

    Yao, L., Mao, C., Luo, Y.: Kg-bert: Bert for knowledge graph completion. CoRR abs/1909.03193(2019)

    arXiv 1909

  75. [75]

    In: NeurIPS

    Yasunaga, M., Bosselut, A., Ren, H., Zhang, X., Manning, C.D., Liang, P.S., Leskovec, J.: Deep bidirectional language-knowledge graph pretraining. In: NeurIPS. pp. 37309–37323 (2022)

    2022

  76. [76]

    In: NAACL- HLT (2021)

    Yasunaga, M., Ren, H., Bosselut, A., Liang, P., Leskovec, J.: Qa-gnn: Reasoning with language models and knowledge graphs for question answering. In: NAACL- HLT (2021)

    2021

  77. [77]

    In: Findings of the Association for Computational Linguistics: EACL (2024) 10 Arijit Khan, Longxu Sun, and Xin Huang

    Ye, R., Zhang, C., Wang, R., Xu, S., Zhang, Y.: Language is all a graph needs. In: Findings of the Association for Computational Linguistics: EACL (2024) 10 Arijit Khan, Longxu Sun, and Xin Huang

    2024

  78. [78]

    In: ICAPS (2025)

    Yu, J., Ding, Y., Sato, H.: Dyntaskmas: A dynamic task graph-driven framework for asynchronous and parallel llm-based multi-agent systems. In: ICAPS (2025)

    2025

  79. [79]

    In: EMNLP (2025)

    Yuan, Z., Liu, M., Wang, H., Qin, B.: MA-GTS: A multi-agent framework for solving complex graph problems in real-world applications. In: EMNLP (2025)

    2025

  80. [80]

    In: WWW (2024)

    Zhang, M., Sun, M., Wang, P., Fan, S., Mo, Y., Xu, X., Liu, H., Yang, C., Shi, C.: Graphtranslator: Aligning graph model to large language model for open-ended tasks. In: WWW (2024)

    2024

Showing first 80 references.