mlsanityData to 14 Oct 2026

A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects

arXiv 2506.11012 ↗First posted 27 Apr 2025cs.AI cs.CLcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Knowledge graphs (KGs) have emerged as a powerful paradigm for structuring and leveraging diverse real-world knowledge, which serve as a fundamental technology for enabling cognitive intelligence systems with advanced understanding and reasoning capabilities. Knowledge graph reasoning (KGR) aims to infer new knowledge based on existing facts in KGs, playing a crucial role in applications such as public security intelligence, intelligent healthcare, and financial risk assessment. From a task-centric perspective, existing KGR approaches can be broadly classified into static single-step KGR, static multi-step KGR, dynamic KGR, multi-modal KGR, few-shot KGR, and inductive KGR. While existing surveys have covered these six types of KGR tasks, a comprehensive review that systematically summarizes all KGR tasks particularly including downstream applications and more challenging reasoning paradigms remains lacking. In contrast to previous works, this survey provides a more comprehensive perspective on the research of KGR by categorizing approaches based on primary reasoning tasks, downstream application tasks, and potential challenging reasoning tasks. Besides, we explore advanced techniques, such as large language models (LLMs), and their impact on KGR. This work aims to highlight key research trends and outline promising future directions in the field of KGR.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 33 of its 470 references that are in the map. First posted on arXiv 27 Apr 2025.

Builds on

33 of 470 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning23 May
  2. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph17 Feb
  3. 2023ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning4 Sep
  4. 2023Complex Logical Reasoning over Knowledge Graphs using Large Language Models2 May

Other references · 29

  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  3. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  4. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  5. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  6. 2024Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Surveycited by 53
  7. 2023Making Large Language Models Perform Better in Knowledge Graph Completioncited by 48
  8. 2023Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphscited by 35
  9. 2019CoKE: Contextualized Knowledge Graph Embeddingcited by 30
  10. 2024A Survey on Temporal Knowledge Graph: Representation Learning and Applicationscited by 30
  11. 2016TensorLog: A Differentiable Deductive Databasecited by 29
  12. 2016Probabilistic Reasoning via Deep Learning: Neural Association Modelscited by 20
17 more
  1. 2015TransA: An Adaptive Approach for Knowledge Graph Embeddingcited by 19
  2. 2022Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspectivecited by 18
  3. 2023A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospectscited by 14
  4. 2024Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completioncited by 10
  5. 2024Negative Sampling in Knowledge Graph Representation Learning: A Reviewcited by 9
  6. 2022Hierarchical Relational Learning for Few-Shot Knowledge Graph Completioncited by 6
  7. 2023A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledgecited by 6
  8. 2015RDF2Rules: Learning Rules from RDF Knowledge Bases by Mining Frequent Predicate Cyclescited by 5
  9. 2019Distributional Negative Sampling for Knowledge Base Completioncited by 5
  10. 2021Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoningcited by 5
  11. 2022Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embeddingcited by 4
  12. 2024Find The Gap: Knowledge Base Reasoning For Visual Question Answeringcited by 4
  13. 2022LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddingscited by 2
  14. 2023Pre-training Transformers for Knowledge Graph Completioncited by 2
  15. 2023Beyond Transduction: A Survey on Inductive, Few Shot, and Zero Shot Link Prediction in Knowledge Graphscited by 2
  16. 2022Walk-and-Relate: A Random-Walk-based Algorithm for Representation Learning on Sparse Knowledge Graphscited by 1
  17. 2025Diffusion-based Hierarchical Negative Sampling for Multimodal Knowledge Graph Completioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models
  2. 2025Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
  3. 2024Synergizing Knowledge Graphs with Large Language Models: A Comprehensive Review and Future Prospects ↗
  4. 2023Knowledge Graphs are not Created Equal: Exploring the Properties and Structure of Real KGs
  5. 2025KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  7. 2025PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models
  8. 2025Towards Unified Neurosymbolic Reasoning on Knowledge Graphs