Pith. sign in

REVIEW 36 cited by

Graph Retrieval-Augmented Generation: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.08921 v2 pith:OSGQRSO7 submitted 2024-08-15 cs.AI cs.CLcs.IR

Graph Retrieval-Augmented Generation: A Survey

classification cs.AI cs.CLcs.IR
keywords graphraggenerationknowledgechallengescomprehensiveentitiesfieldinformation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM outputs, effectively mitigating issues such as ``hallucination'', lack of domain-specific knowledge, and outdated information. However, the complex structure of relationships among different entities in databases presents challenges for RAG systems. In response, GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given the novelty and potential of GraphRAG, a systematic review of current technologies is imperative. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation. We then outline the core technologies and training methods at each stage. Additionally, we examine downstream tasks, application domains, evaluation methodologies, and industrial use cases of GraphRAG. Finally, we explore future research directions to inspire further inquiries and advance progress in the field. In order to track recent progress in this field, we set up a repository at \url{https://github.com/pengboci/GraphRAG-Survey}.

discussion (0)

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

Forward citations

Cited by 36 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

    cs.CL 2026-07 conditional novelty 7.0

    On a 28-tier nested enterprise corpus, BM25 becomes the most accurate scalable RAG retriever after ~10M tokens, beating an agentic file-search system by ~20 points at 601M tokens and remaining low-cost.

  2. ROZA Graphs: Self-Improving Near-Deterministic RAG through Evidence-Centric Feedback

    cs.AI 2026-04 unverdicted novelty 7.0

    ROZA graphs enable self-improving RAG by storing evidence-specific reasoning chains, yielding up to 10.6pp accuracy gains and 46% lower cost through graph traversal feedback.

  3. DOTRAG: Retrieval-Time Reasoning Along Paths

    cs.IR 2026-04 unverdicted novelty 7.0

    DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.

  4. Retrieval Augmented Conversational Recommendation with Reinforcement Learning

    cs.IR 2026-04 unverdicted novelty 7.0

    RAR retrieves candidate items from a 300k-movie corpus then uses LLM generation with RL feedback to produce context-aware recommendations that outperform baselines on benchmarks.

  5. Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling

    cs.AI 2026-04 unverdicted novelty 7.0

    Repurposing competency questions as runtime executable plans creates a controlled neuro-symbolic RAG architecture that produces evidence-closed stories from knowledge graphs.

  6. Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems

    cs.AI 2026-07 conditional novelty 6.0

    Modeling agent trajectories as action-centric probabilistic graphs lets a GNN warn LLM agents of likely step-level errors before execution, improving pass ratio ~14.7% across four benchmarks.

  7. KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval

    cs.IR 2026-07 conditional novelty 6.0

    Partial-alignment contrastive pretraining plus anchor-then-expand graph retrieval improves multi-hop KG evidence recovery and downstream QA over strong dense and graph RAG baselines.

  8. BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

    cs.CL 2026-07 conditional novelty 6.0

    On an enterprise corpus scaled from 1.7M to 601M tokens, BM25 beats raw-file agentic search, dense retrieval, and graph RAG at large sizes, crossing near 10M tokens.

  9. FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data Analysis

    cs.IR 2026-07 conditional novelty 6.0

    Embedding FAIR Digital Objects as graph nodes yields a GraphRAG system that measurably improves accuracy, coverage and explainability on biomedical RNA-seq queries versus a non-FAIR baseline.

  10. Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization

    cs.CL 2026-06 unverdicted novelty 6.0

    Evaluates 9 RAG scenarios across variants, proposes context engineering reducing token usage 19-53%, and identifies a retrieval-generation gap where more retrieval does not improve generation proportionally.

  11. A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation

    cs.AI 2026-06 unverdicted novelty 6.0

    HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% ave...

  12. EfficientGraph-RAG: Structured Retrieval-State Management for Cross-Task Retrieval-Augmented Generation

    cs.CL 2026-05 unverdicted novelty 6.0

    EfficientGraph-RAG structures retrieval state with TAM, MARS and SMP, ranking first on averaged LongBench answer-quality metrics while cutting token use 3.51x on HotpotQA.

  13. Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables

    cs.AI 2026-05 unverdicted novelty 6.0

    Empirical 2x2 factorial study on 6 statistical datasets shows format and schema constraints in LLM-based KG construction from CSV tables produce super-additive fidelity loss up to +1.180, with mismatched pairs falling...

  14. GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

    cs.IR 2026-05 unverdicted novelty 6.0

    GRACE-RAG is a governed graph-augmented RAG architecture that moves structural reasoning to retrieval, reporting up to 20% quality gains on mid-scale models in closed-domain settings.

  15. EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation

    cs.DB 2026-04 unverdicted novelty 6.0

    EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.

  16. Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models

    cs.CL 2026-04 unverdicted novelty 6.0

    OKH-RAG represents knowledge as ordered hyperedges and retrieves coherent interaction sequences via a learned transition model, outperforming permutation-invariant RAG baselines on order-sensitive QA tasks.

  17. Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework

    cs.CL 2026-04 unverdicted novelty 6.0

    A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.

  18. Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation

    cs.LG 2025-10 unverdicted novelty 6.0

    A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.

  19. KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification

    cs.CL 2025-05 unverdicted novelty 6.0

    KG-HTC integrates knowledge graphs into LLMs via RAG to improve zero-shot hierarchical text classification performance on WoS, DBpedia, and Amazon datasets.

  20. In-depth Analysis of Graph-based RAG in a Unified Framework

    cs.IR 2025-03 unverdicted novelty 6.0

    A unified framework and large-scale comparison of graph-based RAG methods on QA tasks yields new high-performing variants obtained by recombining existing components.

  21. ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation

    cs.IR 2025-02 unverdicted novelty 6.0

    ArchRAG proposes attributed-community hierarchical indexing and LLM clustering to improve accuracy and lower token usage in graph-based retrieval-augmented generation.

  22. PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling

    cs.LG 2026-07 conditional novelty 5.0

    PIER augments embedding-based retrieval for lake modeling with a physics-aware stream scored by local verifiers, improving water temperature and dissolved oxygen prediction across 356 lakes.

  23. Enhancing Relation Modeling with Social Attributes for Social Media Popularity Prediction

    cs.MM 2026-07 conditional novelty 5.0

    RE-Rag blends semantic and social-attribute relations in retrieval and attention, achieving lower prediction error than prior RAG-based models on large popularity-prediction benchmarks.

  24. CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

    cs.IR 2026-06 unverdicted novelty 5.0

    CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced ev...

  25. SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs

    cs.AI 2026-06 conditional novelty 5.0

    SCAIR, a training-free schema-conditioned agentic KG-RAG method, substantially outperforms existing KG-RAG approaches on a new enterprise CMDB benchmark, but the evaluation has notable confounds.

  26. STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation

    cs.IR 2026-04 unverdicted novelty 5.0

    STAR is a semantic-tuned and tail-adaptive retriever for GraphRAG that uses cross-attention interaction learning and path-weighted contrastive learning to mitigate Semantic Shortcut Bias and Long-Tail Path Bias, repor...

  27. Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations

    physics.plasm-ph 2026-04 unverdicted novelty 5.0

    Plasma GraphRAG automates physics-grounded parameter selection for gyrokinetic simulations via a domain-specific knowledge graph and LLMs, reporting over 10% better quality and up to 25% fewer hallucinations than stan...

  28. RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

    cs.CL 2025-10 unverdicted novelty 5.0

    RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.

  29. G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge

    cs.AI 2025-09 unverdicted novelty 5.0

    G-reasoner uses QuadGraph abstraction and a 34M-parameter graph foundation model integrated with LLMs to enable scalable reasoning over diverse graph-structured knowledge, outperforming baselines on six benchmarks.

  30. Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models

    cs.CL 2025-01 unverdicted novelty 5.0

    LGPT and Early Query Fusion create flexible graph representations for LLMs, achieving 4.13% improvement on GraphQA without training the model.

  31. Aethel: A Reproducible Graph-Retrieval Framework for Multi-Hop Financial Diligence

    cs.IR 2026-07 conditional novelty 4.0

    Graph retrieval improves multi-hop passage recall in small closed pools but does not beat BM25 on a 4,123-chunk open financial corpus.

  32. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.

  33. A Community Survey on SHACL and ShEx: Briding Gaps in RDF Validation

    cs.DB 2026-06 unverdicted novelty 4.0

    A survey of RDF validation users finds the technology is valued for data quality but needs better documentation, tool support, performance, and expressiveness for complex tasks.

  34. SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction

    cs.IR 2026-05 unverdicted novelty 4.0

    SchemaRAG dynamically reduces large schemas via RAG for LLM information extraction, reporting up to 8.8% micro-F1 gain, 47% latency cut, and 48% token cost reduction on healthcare and e-commerce data.

  35. KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks

    cs.SE 2026-04 unverdicted novelty 4.0

    KnowPilot integrates knowledge retrieval and memory systems into generative agents to achieve better results on domain-specific tasks such as text generation.

  36. Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

    cs.CL 2026-04 unverdicted novelty 4.0

    The survey unifies LLM augmentation techniques along the single axis of structured context supplied at inference time and supplies a literature screening protocol plus deployment decision framework.