mlsanityData to 7 Oct 2026

Synergizing RAG and Reasoning: A Systematic Review

arXiv 2504.15909 ↗First posted 22 Apr 2025cs.IRcited by 27

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

also in 1 more
Abstract (arXiv)

Recent breakthroughs in large language models (LLMs), particularly in reasoning capabilities, have propelled Retrieval-Augmented Generation (RAG) to unprecedented levels. By synergizing retrieval mechanisms with advanced reasoning, LLMs can now tackle increasingly complex problems. This paper presents a systematic review of the collaborative interplay between RAG and reasoning, clearly defining "reasoning" within the RAG context. It construct a comprehensive taxonomy encompassing multi-dimensional collaborative objectives, representative paradigms, and technical implementations, and analyze the bidirectional synergy methods. Additionally, we critically evaluate current limitations in RAG assessment, including the absence of intermediate supervision for multi-step reasoning and practical challenges related to cost-risk trade-offs. To bridge theory and practice, we provide practical guidelines tailored to diverse real-world applications. Finally, we identify promising research directions, such as graph-based knowledge integration, hybrid model collaboration, and RL-driven optimization. Overall, this work presents a theoretical framework and practical foundation to advance RAG systems in academia and industry, fostering the next generation of RAG solutions.

Key facts. Cited by 27 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 88 of its 110 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

88 of 110 references.

Closest ancestors · 21

Same direction, newest first

  1. 2025RARE: Retrieval-Augmented Reasoning Modeling30 Mar
  2. 2025ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation27 Mar
  3. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search26 Mar
  4. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning25 Mar
  5. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  6. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning3 Mar
  7. 2025MCTS-KBQA: Monte Carlo Tree Search with Information Gain Rewards for Knowledge Base Question Answering19 Feb
  8. 2025O1 Embedder: Let Retrievers Think Before Action11 Feb
  9. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Models3 Feb
  10. 2025Chain-of-Retrieval Augmented Generation24 Jan
  11. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs17 Jan
  12. 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking16 Jan
9 more
  1. 2025ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding14 Jan
  2. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  3. 2025Retrieval-Augmented Generation by Evidence Retroactivity in LLMs7 Jan
  4. 2024RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models3 Dec
  5. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models2 Oct
  6. 2024Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks2 Oct
  7. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation15 Jul
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 67

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  5. 2025s1: Simple test-time scalingcited by 1,311
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  7. 2024OpenAI o1 System Cardcited by 1,220
  8. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  9. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  10. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  11. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  12. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
38 more
  1. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  4. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  5. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  6. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  7. 2025REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalizationcited by 233
  8. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  9. 2023TheoremQA: A Theorem-driven Question Answering datasetcited by 189
  10. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
  11. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 142
  12. 2023CMB: A Comprehensive Medical Benchmark in Chinesecited by 113
  13. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  14. 2025Harnessing Multiple Large Language Models: A Survey on LLM Ensemblecited by 86
  15. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  16. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  17. 2024Can Language Models Solve Olympiad Programming?cited by 70
  18. 2025DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learningcited by 62
  19. 2025Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?cited by 58
  20. 2024Agents' Room: Narrative Generation through Multi-step Collaborationcited by 57
  21. 2024MedCoT: Medical Chain of Thought via Hierarchical Expertcited by 46
  22. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
  23. 2025Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?cited by 43
  24. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  25. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
  26. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  27. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphscited by 38
  28. 2024Set the Clock: Temporal Alignment of Pretrained Language Modelscited by 24
  29. 2025Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoningcited by 23
  30. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)cited by 23
  31. 2025Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answeringcited by 22
  32. 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Searchcited by 21
  33. 2025Supervising the search process produces reliable and generalizable information-seeking agentscited by 20
  34. 2024SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedbackcited by 19
  35. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generationcited by 18
  36. 2024Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrievalcited by 17
  37. 2024DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generationcited by 16
  38. 2025Graph RAG-Tool Fusioncited by 15

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 21; 2026: 6.

27 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2025TRAIL: Trace Reasoning and Agentic Issue Localizationcited by 98
  3. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  4. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 50
  5. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  6. 2025End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoningcited by 10
  7. 2025AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Playcited by 10
  8. 2025Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigmcited by 9
  9. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  10. 2026TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agentscited by 8
  11. 2025HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searchescited by 7
  12. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
15 more
  1. 2025Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verificationcited by 4
  2. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 4
  3. 2025Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledgecited by 3
  4. 2025HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMscited by 3
  5. 2025Structure-Augmented Reasoning Generationcited by 2
  6. 2025REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generationcited by 2
  7. 2025EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusioncited by 2
  8. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answeringcited by 1
  9. 2025CARE-RAG - Clinical Assessment and Reasoning in RAGcited by 0
  10. 2025LightSearcher: Efficient DeepSearch via Experiential Memorycited by 0
  11. 2025Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generationcited by 0
  12. 2026RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigmcited by 0
  13. 2026CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoningcited by 0
  14. 2026Blast Radiuscited by 0
  15. 2026D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
  2. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  3. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  4. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning
  5. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
  6. 2024RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
  7. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  8. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions