mlsanityData to 7 Oct 2026

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

arXiv 2507.09477 ↗First posted 13 Jul 2025cs.CL cs.AIcited by 40

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

also in 2 more
Abstract (arXiv)

Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). Finally, we spotlight emerging Synergized RAG-Reasoning frameworks, where (agentic) LLMs iteratively interleave search and reasoning to achieve state-of-the-art performance across knowledge-intensive benchmarks. We categorize methods, datasets, and open challenges, and outline research avenues toward deeper RAG-Reasoning systems that are more effective, multimodally-adaptive, trustworthy, and human-centric. The collection is available at https://github.com/DavidZWZ/Awesome-RAG-Reasoning.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 131 of its 177 references that are in the map. First posted on arXiv 13 Jul 2025.

Builds on

131 of 177 references.

Closest ancestors · 28

Same direction, newest first

  1. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents23 Jun
  2. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capability30 Apr
  3. 2025ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search15 Apr
  4. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration7 Apr
  5. 2025ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation27 Mar
  6. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search26 Mar
  7. 2025Open Deep Search: Democratizing Search with Open-source Reasoning Agents26 Mar
  8. 2025RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration14 Mar
  9. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  10. 2025ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding14 Jan
  11. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  12. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement17 Dec
16 more
  1. 2024SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering7 Dec
  2. 2024Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations30 Oct
  3. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization11 Oct
  4. 2024GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation11 Oct
  5. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation19 Sep
  6. 2024Improving Retrieval Augmented Language Model with Self-Reasoning29 Jul
  7. 2024BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering28 Jun
  8. 2024Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding18 Jun
  9. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  10. 2024Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction27 Apr
  11. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs10 Apr
  12. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation8 Mar
  13. 2024SciAgent: Tool-augmented Language Models for Scientific Reasoning18 Feb
  14. 2023IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions30 Nov
  15. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph15 Jul
  16. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 103

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  8. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  9. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  10. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  12. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
38 more
  1. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  4. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  5. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  10. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  11. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  12. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  13. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  14. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  15. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  16. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  17. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  18. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  19. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  20. 2021MiniF2F: a cross-system benchmark for formal Olympiad-level mathematicscited by 380
  21. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  22. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  23. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 253
  24. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMscited by 246
  25. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  26. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  27. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 204
  28. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  29. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  30. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  31. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  32. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  33. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  34. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 174
  35. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 171
  36. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  37. 2019BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarizationcited by 155
  38. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150

50 most cited of 103 All 103 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 27.

40 papers.

Sort:

By area:

  1. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agentscited by 19
  2. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 18
  3. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 13
  4. 2026From RAG to Agentic RAG for Faithful Islamic Question Answeringcited by 9
  5. 2026Predicting LLM Output Length via Entropy-Guided Representationscited by 9
  6. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  7. 2025AdmTree: Compressing Lengthy Context with Adaptive Semantic Treescited by 7
  8. 2026EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configurationcited by 7
  9. 2026KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Servingcited by 7
  10. 2025AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Constructioncited by 6
  11. 2025ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoningcited by 6
  12. 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Rewardcited by 6
28 more
  1. 2026Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understandingcited by 6
  2. 2025LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentationcited by 5
  3. 2025Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologiescited by 5
  4. 2026Is Agentic RAG worth it? An experimental comparison of RAG approachescited by 5
  5. 2025Test-time Corpus Feedback: From Retrieval to RAGcited by 3
  6. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generationcited by 3
  7. 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAGcited by 3
  8. 2026Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifierscited by 3
  9. 2026RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skillscited by 3
  10. 2025REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generationcited by 2
  11. 2025Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Frameworkcited by 2
  12. 2025MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extractioncited by 2
  13. 2026Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddingscited by 2
  14. 2026TopoAgent: A Self-Evolving Topological Agent for Multimodal Scientific Reasoningcited by 2
  15. 2025From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascadescited by 1
  16. 2025Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignmentcited by 1
  17. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answeringcited by 1
  18. 2026TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generationcited by 1
  19. 2026RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matchingcited by 1
  20. 2026When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapsecited by 1
  21. 2025AI Driven Discovery of Bio Ecological Mediation in Cascading Heatwave Riskscited by 0
  22. 2026Self-MedRAG: a Self-Reflective Hybrid Retrieval-Augmented Generation Framework for Reliable Medical Question Answeringcited by 0
  23. 2026Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrievalcited by 0
  24. 2026RAG without Forgetting: Continual Query-Infused Key Memorycited by 0
  25. 2026DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generationcited by 0
  26. 2026Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generationcited by 0
  27. 2026NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturingcited by 0
  28. 2026Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
  2. 2025Synergizing RAG and Reasoning: A Systematic Review
  3. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  4. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  5. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
  6. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  7. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
  8. 2025DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router