mlsanityData to 7 Oct 2026

Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

arXiv 2501.09136 ↗First posted 15 Jan 2025cs.AI cs.CL cs.IRcited by 242

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs. Retrieval-Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrating real-time data retrieval to provide contextually relevant and up-to-date responses. Despite its promise, traditional RAG systems are constrained by static workflows and lack the adaptability required for multi-step reasoning and complex task management. Agentic Retrieval-Augmented Generation (Agentic RAG) transcends these limitations by embedding autonomous AI agents into the RAG pipeline. These agents leverage agentic design patterns reflection, planning, tool use, and multi-agent collaboration to dynamically manage retrieval strategies, iteratively refine contextual understanding, and adapt workflows through operational structures ranging from sequential steps to adaptive collaboration. This integration enables Agentic RAG systems to deliver flexibility, scalability, and context-awareness across diverse applications. This paper presents an analytical survey of Agentic RAG systems. It traces the evolution of RAG paradigms, introduces a principled taxonomy of Agentic RAG architectures based on agent cardinality, control structure, autonomy, and knowledge representation, and provides a comparative analysis of design trade-offs across existing frameworks. The survey examines applications in healthcare, finance, education, and enterprise document processing, and distills practical lessons for system designers and practitioners. Finally, it identifies key open research challenges related to evaluation, coordination, memory management, efficiency, and governance, outlining directions for future research.

Key facts. Cited by 242 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 37 of its 71 references that are in the map. First posted on arXiv 15 Jan 2025.

Builds on

37 of 71 references.

References · 37

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2016Pointer Sentinel Mixture Modelscited by 2,992
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  9. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  10. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  11. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  12. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
25 more
  1. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  4. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  5. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  6. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  7. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  8. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  9. 2019ELI5: Long Form Question Answeringcited by 567
  10. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  11. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
  12. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  13. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  14. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  15. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  16. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  17. 2019Multi-Sentence Argument Linkingcited by 80
  18. 2024A Complete Survey on LLM-based AI Chatbotscited by 71
  19. 2018Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graphcited by 67
  20. 2016Conditional Generation and Snapshot Learning in Neural Dialogue Systemscited by 17
  21. 2023A Survey of AI Text-to-Image and AI Text-to-Video Generatorscited by 17
  22. 2024Revolutionizing Mental Health Care through LangChain: A Journey with a Large Language Modelcited by 8
  23. 2024Digital Diagnostics: The Potential Of Large Language Models In Recognizing Symptoms Of Common Illnessescited by 8
  24. 2024Exploring Prompt Engineering: A Systematic Review with SWOT Analysiscited by 5
  25. 2024Encouraging Responsible Use of Generative AI in Education: A Reward-Based Learning Approachcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 115; 2026: 127.

242 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 167
  3. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  4. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  5. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 106
  6. 2025StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimizationcited by 82
  7. 2025Time-MQA: Time Series Multi-Task Question Answering with Context Enhancementcited by 74
  8. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learningcited by 68
  9. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 49
  10. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  11. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  12. 2025An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agentscited by 43
38 more
  1. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  2. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoningcited by 37
  3. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agentscited by 36
  4. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interactioncited by 33
  5. 2025Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlookcited by 32
  6. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
  7. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  8. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 30
  9. 2025AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answeringcited by 29
  10. 2025A Survey of Personalization: From RAG to Agentcited by 26
  11. 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Rewardcited by 25
  12. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 25
  13. 2025Get Experience from Practice: LLM Agents with Record & Replaycited by 22
  14. 2025AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulationcited by 21
  15. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  16. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  17. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  18. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  19. 2025InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generationcited by 15
  20. 2025MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inferencecited by 15
  21. 2026Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Trainingcited by 15
  22. 2025CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Executioncited by 14
  23. 2025A Survey on Agent Workflow -- Status and Futurecited by 14
  24. 2025Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learningcited by 13
  25. 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Auditcited by 11
  26. 2026MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chainscited by 11
  27. 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agentscited by 10
  28. 2025End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoningcited by 10
  29. 2025MicroRemed: Benchmarking LLMs in Microservices Remediationcited by 10
  30. 2025X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysiscited by 10
  31. 2025Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and Networkingcited by 9
  32. 2025HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generationcited by 9
  33. 2025Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understandingcited by 9
  34. 2025Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluationcited by 8
  35. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  36. 2026Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairnesscited by 8
  37. 2026ACM: Agentic Context Management for Long Horizon Taskscited by 8
  38. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generationcited by 7

50 most cited of 242 All 242 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  2. 2024A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data
  3. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
  4. 2026GRASP: GRanularity-Aware Search Policy for Agentic RAG
  5. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
  6. 2025RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG
  7. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
  8. 2025Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems