mlsanityData to 7 Oct 2026

Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks

arXiv 2407.21059 ↗First posted 26 Jul 2024cs.CL cs.AI cs.IRcited by 41

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-augmented Generation (RAG) has markedly enhanced the capabilities of Large Language Models (LLMs) in tackling knowledge-intensive tasks. The increasing demands of application scenarios have driven the evolution of RAG, leading to the integration of advanced retrievers, LLMs and other complementary technologies, which in turn has amplified the intricacy of RAG systems. However, the rapid advancements are outpacing the foundational RAG paradigm, with many methods struggling to be unified under the process of "retrieve-then-generate". In this context, this paper examines the limitations of the existing RAG paradigm and introduces the modular RAG framework. By decomposing complex RAG systems into independent modules and specialized operators, it facilitates a highly reconfigurable framework. Modular RAG transcends the traditional linear architecture, embracing a more advanced design that integrates routing, scheduling, and fusion mechanisms. Drawing on extensive research, this paper further identifies prevalent RAG patterns-linear, conditional, branching, and looping-and offers a comprehensive analysis of their respective implementation nuances. Modular RAG presents innovative opportunities for the conceptualization and deployment of RAG systems. Finally, the paper explores the potential emergence of new operators and paradigms, establishing a solid theoretical foundation and a practical roadmap for the continued evolution and practical deployment of RAG technologies.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 50 of its 64 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

50 of 64 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers18 Jun
  2. 2024Multi-Head RAG: Solving Multi-Aspect Problems with LLMs7 Jun
  3. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models17 Apr
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Survey29 Feb
  5. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models30 Jan
  6. 2024The Power of Noise: Redefining Retrieval for RAG Systems26 Jan
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  8. 2023Context Tuning for Retrieval Augmented Generation9 Dec

Other references · 42

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  11. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
30 more
  1. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  2. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  3. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  4. 2023Active Retrieval Augmented Generationcited by 506
  5. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  6. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  7. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  8. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  9. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  10. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 241
  11. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  12. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  13. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  14. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  15. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 95
  16. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  17. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  18. 2020SCATTER: Selective Context Attentional Scene Text Recognizercited by 69
  19. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  20. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 61
  21. 2023PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adaptercited by 38
  22. 2024NoteLLM: A Retrievable Large Language Model for Note Recommendationcited by 33
  23. 2023Retrieval-Generation Synergy Augmented Large Language Modelscited by 26
  24. 2023Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate Systemcited by 26
  25. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  26. 2023Knowledge-Augmented Language Model Verificationcited by 21
  27. 2024Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmarkcited by 19
  28. 2023GAR-meets-RAG Paradigm for Zero-Shot Information Retrievalcited by 18
  29. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
  30. 2022A Bird's-eye View of Reranking: from List Level to Page Levelcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 26; 2026: 9.

41 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  3. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  4. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  5. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 26
  6. 2025U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystackcited by 20
  7. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challengescited by 19
  8. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generationcited by 18
  9. 2025Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systemscited by 18
  10. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systemscited by 9
  11. 2025MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAGcited by 9
  12. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Explorationcited by 7
29 more
  1. 2025Diversity Enhances an LLM's Performance in RAG and Long-context Taskcited by 7
  2. 2025Evaluating the Effect of Retrieval Augmentation on Social Biasescited by 7
  3. 2025MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generationcited by 7
  4. 2025Mitigating Bias in RAG: Controlling the Embeddercited by 6
  5. 2025RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughtscited by 6
  6. 2025WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflectioncited by 6
  7. 2026AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognitioncited by 6
  8. 2025From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMscited by 5
  9. 2025RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learningcited by 5
  10. 2026AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAGcited by 5
  11. 2024Smart Audit System Empowered by LLMcited by 4
  12. 2025Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agentscited by 4
  13. 2024SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answeringcited by 3
  14. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
  15. 2024Exploring Gen-AI applications in building research and industry: A reviewcited by 2
  16. 2025SoDA: An Efficient Interaction Paradigm for the Agentic Webcited by 2
  17. 2026RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systemscited by 2
  18. 2025SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Contextcited by 1
  19. 2025Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMscited by 1
  20. 2025RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAGcited by 1
  21. 2025Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrievalcited by 1
  22. 2026Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimizationcited by 1
  23. 2026Mandol: An Agglomerative Agent Memory System for Long-Term Conversationscited by 1
  24. 2025LLM-Based Config Synthesis requires Disambiguationcited by 0
  25. 2025Should AI Become an Intergenerational Civil Right?cited by 0
  26. 2026HaS: Accelerating RAG through Homology-Aware Speculative Retrievalcited by 0
  27. 2026LeakDojo: Decoding the Leakage Threats of RAG Systemscited by 0
  28. 2026RAGe: A Retrieval-Augmented Generation Evaluation Frameworkcited by 0
  29. 2026Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research
  2. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving
  3. 2025FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation
  4. 2024RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation
  5. 2025RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
  6. 2025Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems
  7. 2026RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
  8. 2025Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration