mlsanityData to 14 Oct 2026

Revisiting RAG Ensemble: A Theoretical and Mechanistic Analysis of Multi-RAG System Collaboration

arXiv 2508.13828 ↗First posted 19 Aug 2025cs.AIcited by 2

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) technology has been widely applied in recent years. However, despite the emergence of various RAG frameworks, a single RAG framework still cannot adapt well to a broad range of downstream tasks. Therefore, how to leverage the advantages of multiple RAG systems has become an area worth exploring. To address this issue, we have conducted a comprehensive and systematic investigation into ensemble methods based on RAG systems. Specifically, we have analyzed the RAG ensemble framework from both theoretical and mechanistic analysis perspectives. From the theoretical analysis, we provide the first explanation of the RAG ensemble framework from the perspective of information entropy. In terms of mechanism analysis, we have explored the RAG ensemble framework from both the pipeline and module levels. We carefully select four different pipelines (Branching, Iterative, Loop, and Agentic) and three different modules (Generator, Retriever, and Reranker) to solve seven different research questions. The experiments show that aggregating multiple RAG systems is both generalizable and robust, whether at the pipeline level or the module level. Our work lays the foundation for similar research on the multi-RAG system ensemble.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 36 of its 63 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

36 of 63 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation26 Jun
  2. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research22 May
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  10. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  12. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
21 more
  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  2. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  3. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  4. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  6. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  8. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  10. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 335
  11. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  12. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 229
  13. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  14. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  15. 2023Large Language Model Routing with Benchmark Datasetscited by 172
  16. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  17. 2024SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengthscited by 75
  18. 2024Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelscited by 73
  19. 2023TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reductioncited by 34
  20. 2024Purifying Large Language Models by Ensembling a Small Language Modelcited by 25
  21. 2024INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuningcited by 20

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Agentic Entropy-Balanced Policy Optimizationcited by 40
  2. 2025Uncertainty Quantification for Retrieval-Augmented Reasoningcited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2025RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
  2. 2024RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
  3. 2025Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems
  4. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks
  5. 2026RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
  6. 2024InspectorRAGet: An Introspection Platform for RAG Evaluation
  7. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  8. 2025EncouRAGe: Evaluating RAG Local, Fast, and Reliable