mlsanityData to 7 Oct 2026

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models

arXiv 2502.01142 ↗First posted 3 Feb 2025cs.AI cs.CL cs.IRcited by 37

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

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) have shown remarkable reasoning capabilities, while their practical applications are limited by severe factual hallucinations due to limitations in the timeliness, accuracy, and comprehensiveness of their parametric knowledge. Meanwhile, enhancing retrieval-augmented generation (RAG) with reasoning remains challenging due to ineffective task decomposition and redundant retrieval, which can introduce noise and degrade response quality. In this paper, we propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP), enabling reasonable and adaptive retrieval. By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step. Experiments show that DeepRAG improves retrieval efficiency and boosts answer accuracy by 26.4%, demonstrating its effectiveness in enhancing retrieval-augmented reasoning.

Key facts. Cited by 37 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 20 of its 41 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

20 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan

Other references · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2019Language Models as Knowledge Bases?cited by 1,922
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  8. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  9. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  10. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  11. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  12. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 107
7 more
  1. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  2. 2023Understanding Retrieval Augmentation for Long-Form Question Answeringcited by 45
  3. 2024Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluationcited by 37
  4. 2024Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generationcited by 21
  5. 2024Divide-or-Conquer? Which Part Should You Distill Your LLM?cited by 17
  6. 2024Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineeringcited by 16
  7. 2025Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 19.

37 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  3. 2025A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Futurecited by 53
  4. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  5. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  6. 2025R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learningcited by 19
  7. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 19
  8. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 14
  9. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answeringcited by 13
  10. 2025Towards Better Instruction Following Retrieval Modelscited by 9
  11. 2025DeepTrans: Deep Reasoning Translation via Reinforcement Learningcited by 8
  12. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
25 more
  1. 2025MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chainscited by 7
  2. 2025Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systemscited by 5
  3. 2025AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learningcited by 5
  4. 2026PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVRcited by 5
  5. 2026OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answeringcited by 5
  6. 2026CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Searchcited by 3
  7. 2026DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoningcited by 2
  8. 2025TrustRAG: An Information Assistant with Retrieval Augmented Generationcited by 1
  9. 2025Multi-hop Reasoning via Early Knowledge Alignmentcited by 1
  10. 2026Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAGcited by 1
  11. 2026Mitigating Hallucination in Financial Retrieval-Augmented Generation via Fine-Grained Knowledge Verificationcited by 1
  12. 2026MiA-Signature: Approximating Global Activation for Long-Context Understandingcited by 1
  13. 2026AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answeringcited by 1
  14. 2025Zero-Shot Event Causality Identification via Multi-source Evidence Fuzzy Aggregation with Large Language Modelscited by 0
  15. 2025Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansioncited by 0
  16. 2025PathFinder: MCTS and LLM Feedback-based Path Selection for Multi-Hop Question Answeringcited by 0
  17. 2026TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thoughtcited by 0
  18. 2026FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzingcited by 0
  19. 2026Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Studycited by 0
  20. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0
  21. 2026PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agentcited by 0
  22. 2026Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answeringcited by 0
  23. 2026Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAGcited by 0
  24. 2026Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAGcited by 0
  25. 2026TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
  2. 2024AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant
  3. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  4. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  5. 2025Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
  6. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  7. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
  8. 2025Retrieval-augmented reasoning with lean language models