mlsanityData to 14 Oct 2026

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

arXiv 2410.08815 ↗First posted 11 Oct 2024cs.CL cs.AIcited by 71

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

also in 1 more
Abstract (arXiv)

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-intensive reasoning, we proposes a new framework, StructRAG, which can identify the optimal structure type for the task at hand, reconstruct original documents into this structured format, and infer answers based on the resulting structure. Extensive experiments across various knowledge-intensive tasks show that StructRAG achieves state-of-the-art performance, particularly excelling in challenging scenarios, demonstrating its potential as an effective solution for enhancing LLMs in complex real-world applications.

Key facts. Cited by 71 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 30 of its 41 references that are in the map. First posted on arXiv 11 Oct 2024.

Builds on

30 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 29

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  6. 2023Active Retrieval Augmented Generationcited by 516
  7. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  8. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
  9. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  10. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 215
  11. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 160
  12. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 122
17 more
  1. 2020A Survey of Knowledge-Enhanced Text Generationcited by 120
  2. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  3. 2023A Multi-Task Embedder For Retrieval Augmented LLMscited by 64
  4. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  5. 2019Answering Complex Open-domain Questions Through Iterative Query Generationcited by 60
  6. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  7. 2024Confabulation: The Surprising Value of Large Language Model Hallucinationscited by 43
  8. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  9. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  10. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  11. 2021Cross-Modal Retrieval Augmentation for Multi-Modal Classificationcited by 20
  12. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  13. 2024CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Taskscited by 18
  14. 2024BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimizationcited by 18
  15. 2023A Sequence-to-Sequence&Set Model for Text-to-Table Generationcited by 16
  16. 2024Structsum Generation for Faster Text Comprehensioncited by 9
  17. 2024Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 33; 2026: 36.

71 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  2. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  3. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 48
  4. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 47
  5. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  6. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 29
  7. 2024Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineeringcited by 16
  8. 2025MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphscited by 16
  9. 2025Graph RAG-Tool Fusioncited by 15
  10. 2025AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understandingcited by 15
  11. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answeringcited by 12
  12. 2025LAG: Logic-Augmented Generation from a Cartesian Perspectivecited by 10
38 more
  1. 2025DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinkingcited by 9
  2. 2025Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generationcited by 9
  3. 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAGcited by 8
  4. 2026SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Executioncited by 8
  5. 2025Grounding LLM Reasoning with Knowledge Graphscited by 7
  6. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQAcited by 7
  7. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 7
  8. 2025AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMscited by 7
  9. 2026Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAGcited by 7
  10. 2025AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discoverycited by 6
  11. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generationcited by 5
  12. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challengescited by 3
  13. 2026Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneckcited by 3
  14. 2026Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrievalcited by 3
  15. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphscited by 3
  16. 2026DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answeringcited by 3
  17. 2025Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generationcited by 2
  18. 2025Structure-Augmented Reasoning Generationcited by 2
  19. 2025Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generationcited by 2
  20. 2025Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Frameworkcited by 2
  21. 2025HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representationscited by 2
  22. 2026Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoningcited by 2
  23. 2025TrustRAG: An Information Assistant with Retrieval Augmented Generationcited by 1
  24. 2025SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMscited by 1
  25. 2025PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexingcited by 1
  26. 2025TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representationscited by 1
  27. 2026Disco-RAG: Discourse-Aware Retrieval-Augmented Generationcited by 1
  28. 2026PhyNiKCE: A Neurosymbolic Agentic Framework for Autonomous Computational Fluid Dynamicscited by 1
  29. 2026GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generationcited by 1
  30. 2026DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memorycited by 1
  31. 2026SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedgescited by 1
  32. 2026MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memorycited by 1
  33. 2026EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answeringcited by 1
  34. 2025A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generationcited by 0
  35. 2025KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAGcited by 0
  36. 2025Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extractioncited by 0
  37. 2025jXBW: A Compressed Index Enabling Structure-Aware JSONL Retrieval for Structured RAGcited by 0
  38. 2025PluriHopRAG: Exhaustive, Recall-Sensitive QA Through Corpus-Specific Document Structure Learningcited by 0

50 most cited of 71 All 71 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
  2. 2025RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
  3. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
  4. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  5. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  6. 2025Synergizing RAG and Reasoning: A Systematic Review
  7. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
  8. 2026Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs