mlsanityData to 7 Oct 2026

Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning

arXiv 2503.01642 ↗First posted 3 Mar 2025cs.AIcited by 8

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

Abstract (arXiv)

Recent large language model (LLM) reasoning, despite its success, suffers from limited domain knowledge, susceptibility to hallucinations, and constrained reasoning depth, particularly in small-scale models deployed in resource-constrained environments. This paper presents the first investigation into integrating step-wise knowledge graph retrieval with step-wise reasoning to address these challenges, introducing a novel paradigm termed as graph-augmented reasoning. Our goal is to enable frozen, small-scale LLMs to retrieve and process relevant mathematical knowledge in a step-wise manner, enhancing their problem-solving abilities without additional training. To this end, we propose KG-RAR, a framework centered on process-oriented knowledge graph construction, a hierarchical retrieval strategy, and a universal post-retrieval processing and reward model (PRP-RM) that refines retrieved information and evaluates each reasoning step. Experiments on the Math500 and GSM8K benchmarks across six models demonstrate that KG-RAR yields encouraging results, achieving a 20.73% relative improvement with Llama-3B on Math500.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 91 of its 108 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

91 of 108 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration6 Nov
  2. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models16 Oct
  3. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation8 Mar
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  5. 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Model9 Oct
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning2 Oct
  7. 2023LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities22 May
  8. 2023Complex Logical Reasoning over Knowledge Graphs using Large Language Models2 May

Other references · 83

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  10. 2024Qwen2.5 Technical Reportcited by 4,713
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  12. 2023Let's Verify Step by Stepcited by 3,598
38 more
  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  2. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  5. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  7. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  9. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  10. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  11. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  12. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  13. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  14. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  15. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  16. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  17. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 533
  18. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  19. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 465
  20. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  21. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  22. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  23. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 329
  24. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
  25. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  26. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  27. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 283
  28. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruningcited by 278
  29. 2024ProcessBench: Identifying Process Errors in Mathematical Reasoningcited by 277
  30. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  31. 2023Reward Design with Language Modelscited by 257
  32. 2023Large Language Model Alignment: A Surveycited by 241
  33. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 217
  34. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  35. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  36. 2022DocPrompting: Generating Code by Retrieving the Docscited by 151
  37. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  38. 2024Generative Reward Modelscited by 148

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  3. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  4. 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 36
  5. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  6. 2025LLM-empowered knowledge graph construction: A surveycited by 20
  7. 2026VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detectioncited by 0
  8. 2026eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning
  2. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  3. 2025Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
  4. 2025PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models
  5. 2025Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners
  6. 2025Grounding LLM Reasoning with Knowledge Graphs
  7. 2023GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach
  8. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs