mlsanityData to 14 Oct 2026

A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions

arXiv 2507.18910 ↗First posted 25 Jul 2025cs.CL cs.LGcited by 31

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) represents a major advancement in natural language processing (NLP), combining large language models (LLMs) with information retrieval systems to enhance factual grounding, accuracy, and contextual relevance. This paper presents a comprehensive systematic review of RAG, tracing its evolution from early developments in open domain question answering to recent state-of-the-art implementations across diverse applications. The review begins by outlining the motivations behind RAG, particularly its ability to mitigate hallucinations and outdated knowledge in parametric models. Core technical components-retrieval mechanisms, sequence-to-sequence generation models, and fusion strategies are examined in detail. A year-by-year analysis highlights key milestones and research trends, providing insight into RAG's rapid growth. The paper further explores the deployment of RAG in enterprise systems, addressing practical challenges related to retrieval of proprietary data, security, and scalability. A comparative evaluation of RAG implementations is conducted, benchmarking performance on retrieval accuracy, generation fluency, latency, and computational efficiency. Persistent challenges such as retrieval quality, privacy concerns, and integration overhead are critically assessed. Finally, the review highlights emerging solutions, including hybrid retrieval approaches, privacy-preserving techniques, optimized fusion strategies, and agentic RAG architectures. These innovations point toward a future of more reliable, efficient, and context-aware knowledge-intensive NLP systems.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 72 of its 94 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

72 of 94 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG8 Oct
  2. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach23 Jul
  3. 2024FACTS About Building Retrieval Augmented Generation-based Chatbots10 Jul
  4. 2024Ragnar"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track24 Jun
  5. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generation21 Apr
  6. 2024ARAGOG: Advanced RAG Output Grading1 Apr
  7. 2024Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge3 Mar
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Survey29 Feb
  9. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries27 Jan
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  11. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory3 May

Other references · 61

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  11. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  12. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
38 more
  1. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  2. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  3. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  4. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  5. 2019Passage Re-ranking with BERTcited by 645
  6. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
  7. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  8. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  9. 2023Active Retrieval Augmented Generationcited by 516
  10. 2014Memory Networkscited by 363
  11. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  12. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  13. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  14. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  15. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  16. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  17. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 198
  18. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 176
  19. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  20. 2021Retrieval Augmented Code Generation and Summarizationcited by 149
  21. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  22. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 128
  23. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 127
  24. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  25. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  26. 2020Pre-training via Paraphrasingcited by 92
  27. 2021Federated Learning: Opportunities and Challengescited by 84
  28. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
  29. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  30. 2024CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answeringcited by 72
  31. 2024Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agentcited by 65
  32. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
  33. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insightscited by 53
  34. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  35. 2024Interactive AI with Retrieval-Augmented Generation for Next Generation Networkingcited by 34
  36. 2025SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Modelcited by 32
  37. 2025Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicingcited by 25
  38. 2024CPR: Retrieval Augmented Generation for Copyright Protectioncited by 24

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 21.

31 papers.

Sort:

By area:

  1. 2025HaluMem: Evaluating Hallucinations in Memory Systems of Agentscited by 54
  2. 2026TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agentscited by 8
  3. 2025Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoderscited by 7
  4. 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledgecited by 5
  5. 2025Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metricscited by 4
  6. 2025Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgetscited by 3
  7. 2026CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact Assessmentcited by 3
  8. 2025Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generationcited by 2
  9. 2026Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Modelscited by 2
  10. 2025MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systemscited by 1
  11. 2026A3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activationcited by 1
  12. 2026HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generationcited by 1
19 more
  1. 2026PRECTR-V2:Unified Relevance-CTR Framework with Cross-User Preference Mining, Exposure Bias Correction, and LLM-Distilled Encoder Optimizationcited by 1
  2. 2026AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systemscited by 1
  3. 2026Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Researchcited by 1
  4. 2026Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generationcited by 1
  5. 2026The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIFcited by 1
  6. 2026Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?cited by 1
  7. 2026Designing Agent-Ready Websites for AI Web Agents: A Framework for Machine Readability, Actionability, and Decision Reliabilitycited by 1
  8. 2025Role of Large Language Models and Retrieval-Augmented Generation for Accelerating Crystalline Material Discovery: A Systematic Reviewcited by 0
  9. 2025RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answeringcited by 0
  10. 2025Should AI Become an Intergenerational Civil Right?cited by 0
  11. 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigmscited by 0
  12. 2026Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problemcited by 0
  13. 2025Retrieval-Augmented Generation Assistant for Anatomical Pathology Laboratoriescited by 0
  14. 2026The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AIcited by 0
  15. 2026SentAttack: A Sentence-Level Black-Box Adversarial Attack Method for Dense Retrieval Modelscited by 0
  16. 2026Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurtscited by 0
  17. 2026Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignmentcited by 0
  18. 2026FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Explorationcited by 0
  19. 2026Configuring RAG Systems: What Breaks, Where Originates, and How to Fixcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  2. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
  3. 2024Evaluation of Retrieval-Augmented Generation: A Survey
  4. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  5. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey
  6. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  7. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  8. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models