mlsanityData to 14 Oct 2026

Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges

arXiv 2506.10408 ↗First posted 12 Jun 2025cs.AI cs.IRcited by 19

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

also in 2 more
Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG systems based on static pipelines have shown effectiveness in well-structured tasks, they struggle in real-world scenarios requiring complex reasoning, dynamic retrieval, and multi-modal integration. To address these challenges, the field has shifted toward Reasoning Agentic RAG, a paradigm that embeds decision-making and adaptive tool use directly into the retrieval process. In this paper, we present a comprehensive review of Reasoning Agentic RAG methods, categorizing them into two primary systems: predefined reasoning, which follows fixed modular pipelines to boost reasoning, and agentic reasoning, where the model autonomously orchestrates tool interaction during inference. We analyze representative techniques under both paradigms, covering architectural design, reasoning strategies, and tool coordination. Finally, we discuss key research challenges and propose future directions to advance the flexibility, robustness, and applicability of reasoning agentic RAG systems. Our collection of the relevant research has been organized into a https://github.com/ByebyeMonica/Reasoning-Agentic-RAG.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 50 references that are in the map. First posted on arXiv 12 Jun 2025.

Builds on

34 of 50 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  2. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 30

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2023A Survey of Large Language Modelscited by 2,576
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  10. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  11. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  12. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
18 more
  1. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  2. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 245
  3. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  4. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  5. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  6. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 131
  7. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
  8. 2024CRAG -- Comprehensive RAG Benchmarkcited by 97
  9. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
  10. 2025DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learningcited by 66
  11. 2025Retrieval-Augmented Generation with Conflicting Evidencecited by 63
  12. 2023Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answeringcited by 51
  13. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 42
  14. 2023Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approachcited by 38
  15. 2024Are Large Language Models Good Statisticians?cited by 27
  16. 2024Adaptive Retrieval-Augmented Generation for Conversational Systemscited by 22
  17. 2024Agentic Retrieval-Augmented Generation for Time Series Analysiscited by 14
  18. 2024LLM2: Let Large Language Models Harness System 2 Reasoningcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 12.

19 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  3. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 22
  4. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 20
  5. 2026From RAG to Agentic RAG for Faithful Islamic Question Answeringcited by 9
  6. 2025Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generationcited by 6
  7. 2026AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAGcited by 5
  8. 2025Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMscited by 4
  9. 2026Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspectivecited by 4
  10. 2025Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generationcited by 2
  11. 2026Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibrationcited by 1
  12. 2026DOTRAG: Retrieval-Time Reasoning Along Pathscited by 1
7 more
  1. 2026FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&Acited by 1
  2. 2025SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novelscited by 0
  3. 2026Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrievalcited by 0
  4. 2026DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answeringcited by 0
  5. 2026Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspectivecited by 0
  6. 2026Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Storescited by 0
  7. 2026Follow the Entities: A Corpus Map for Agentic Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
  2. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  3. 2025Synergizing RAG and Reasoning: A Systematic Review
  4. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
  5. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
  6. 2026Is Agentic RAG worth it? An experimental comparison of RAG approaches
  7. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  8. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning