mlsanityData to 14 Oct 2026

Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

arXiv 2407.10805 ↗First posted 15 Jul 2024cs.CL cs.AIcited by 64

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) has improved large language models (LLMs) by using knowledge retrieval to overcome knowledge deficiencies. However, current RAG methods often fall short of ensuring the depth and completeness of retrieved information, which is necessary for complex reasoning tasks. In this work, we introduce Think-on-Graph 2.0 (ToG-2), a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources in a tight-coupling manner. Specifically, ToG-2 leverages knowledge graphs (KGs) to link documents via entities, facilitating deep and knowledge-guided context retrieval. Simultaneously, it utilizes documents as entity contexts to achieve precise and efficient graph retrieval. ToG-2 alternates between graph retrieval and context retrieval to search for in-depth clues relevant to the question, enabling LLMs to generate answers. We conduct a series of well-designed experiments to highlight the following advantages of ToG-2: 1) ToG-2 tightly couples the processes of context retrieval and graph retrieval, deepening context retrieval via the KG while enabling reliable graph retrieval based on contexts; 2) it achieves deep and faithful reasoning in LLMs through an iterative knowledge retrieval process of collaboration between contexts and the KG; and 3) ToG-2 is training-free and plug-and-play compatible with various LLMs. Extensive experiments demonstrate that ToG-2 achieves overall state-of-the-art (SOTA) performance on 6 out of 7 knowledge-intensive datasets with GPT-3.5, and can elevate the performance of smaller models (e.g., LLAMA-2-13B) to the level of GPT-3.5's direct reasoning. The source code is available on https://github.com/IDEA-FinAI/ToG-2.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 31 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

24 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph15 Jul
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 21

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  7. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  10. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  11. 2019Knowledge Enhanced Contextual Word Representationscited by 296
  12. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
9 more
  1. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  2. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  3. 2021CREAK: A Dataset for Commonsense Reasoning over Entity Knowledgecited by 88
  4. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
  5. 2020SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Basescited by 47
  6. 2024Entropy-Based Decoding for Retrieval-Augmented Large Language Modelscited by 19
  7. 2024Efficient Knowledge Infusion via KG-LLM Alignmentcited by 13
  8. 2024Joint Multi-Facts Reasoning Network For Complex Temporal Question Answering Over Knowledge Graphcited by 6
  9. 2024The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 34; 2026: 28.

64 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  3. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  4. 2026Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agentscited by 23
  5. 2025A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworkscited by 21
  6. 2025Reasoning of Large Language Models over Knowledge Graphs with Super-Relationscited by 21
  7. 2025RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generationcited by 16
  8. 2025LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Datacited by 16
  9. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoningcited by 15
  10. 2026PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environmentscited by 14
  11. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrievalcited by 10
  12. 2025Multi-agent systems for chemical engineering: A review and perspectivecited by 9
38 more
  1. 2025Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understandingcited by 9
  2. 2026InfMem: Learning System-2 Memory Control for Long-Context Agentcited by 9
  3. 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?cited by 8
  4. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databasescited by 7
  5. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 7
  6. 2025TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Frameworkcited by 7
  7. 2025DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTScited by 6
  8. 2026GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculumcited by 6
  9. 2025DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillationcited by 5
  10. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answeringcited by 5
  11. 2025Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Modelscited by 4
  12. 2025KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervisioncited by 4
  13. 2025Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answeringcited by 3
  14. 2025MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generationcited by 3
  15. 2025CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineeringcited by 3
  16. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
  17. 2025KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answeringcited by 3
  18. 2026Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checkingcited by 3
  19. 2025R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphscited by 2
  20. 2025KAQG: A Knowledge-Graph-Enhanced RAG for Difficulty-Controlled Question Generationcited by 2
  21. 2025Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walkscited by 2
  22. 2025XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generationcited by 2
  23. 2025PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agentscited by 2
  24. 2025Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generationcited by 2
  25. 2025PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generationcited by 2
  26. 2026Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Modelscited by 2
  27. 2024Semantic Parsing with Candidate Expressions for Knowledge Base Question Answeringcited by 1
  28. 2025SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Contextcited by 1
  29. 2025RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QAcited by 1
  30. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphscited by 1
  31. 2026FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systemscited by 1
  32. 2026MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generationcited by 1
  33. 2026Knowledge Capsules: Structured Nonparametric Memory Units for LLMscited by 1
  34. 2025LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Rankingcited by 0
  35. 2026A Navigational Approach for Comprehensive RAG via Traversal over Proposition Graphscited by 0
  36. 2026Life-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognitioncited by 0
  37. 2026TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answeringcited by 0
  38. 2026CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answeringcited by 0

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  2. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  3. 2025GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
  4. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  5. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  6. 2025Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
  7. 2026UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
  8. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey