mlsanityData to 14 Oct 2026

M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions

arXiv 2405.16420 ↗First posted 26 May 2024cs.CL cs.IRcited by 38

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database. However, existing RAG methods typically organize all memories in a whole database, potentially limiting focus on crucial memories and introducing noise. In this paper, we introduce a multiple partition paradigm for RAG (called M-RAG), where each database partition serves as a basic unit for RAG execution. Based on this paradigm, we propose a novel framework that leverages LLMs with Multi-Agent Reinforcement Learning to optimize different language generation tasks explicitly. Through comprehensive experiments conducted on seven datasets, spanning three language generation tasks and involving three distinct language model architectures, we confirm that M-RAG consistently outperforms various baseline methods, achieving improvements of 11%, 8%, and 12% for text summarization, machine translation, and dialogue generation, respectively.

Key facts. Cited by 38 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 38 of its 64 references that are in the map. First posted on arXiv 26 May 2024.

Builds on

38 of 64 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory3 May

Other references · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  9. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  10. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  11. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  12. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
24 more
  1. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  2. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  3. 2019Introduction to Multi-Armed Banditscited by 481
  4. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  5. 2021Recursively Summarizing Books with Human Feedbackcited by 290
  6. 2019Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialogcited by 284
  7. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  8. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  9. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  10. 2019BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarizationcited by 156
  11. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 133
  12. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 75
  13. 2018Can Neural Machine Translation be Improved with User Feedback?cited by 72
  14. 2020SCATTER: Selective Context Attentional Scene Text Recognizercited by 69
  15. 2022Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Datacited by 61
  16. 2023A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challengecited by 55
  17. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  18. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  19. 2023LM-Cocktail: Resilient Tuning of Language Models via Model Mergingcited by 44
  20. 2019Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluatorscited by 35
  21. 2018Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedbackcited by 32
  22. 2023Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Datacited by 23
  23. 2024Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedbackcited by 9
  24. 2023Collectively Simplifying Trajectories in a Database: A Query Accuracy Driven Approachcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 16; 2026: 18.

38 papers.

Sort:

By area:

  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  2. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 71
  3. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agentscited by 52
  4. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 51
  5. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  6. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphscited by 38
  7. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontierscited by 27
  8. 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systemscited by 20
  9. 2025HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devicescited by 15
  10. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 7
  11. 2024CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAGcited by 6
  12. 2026HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolutioncited by 6
26 more
  1. 2025Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generatorcited by 4
  2. 2025REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processingcited by 4
  3. 2025TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domaincited by 4
  4. 2024A Scalable Data-Driven Framework for Systematic Analysis of SEC 10-K Filings Using Large Language Modelscited by 3
  5. 2026Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Modelscited by 3
  6. 2026BMAM: Brain-inspired Multi-Agent Memory Frameworkcited by 3
  7. 2026ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Contextcited by 3
  8. 2025RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systemscited by 2
  9. 2026Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAGcited by 2
  10. 2026IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Reviewcited by 2
  11. 2025Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Stylecited by 1
  12. 2025From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascadescited by 1
  13. 2025A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchaincited by 1
  14. 2025Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrievalcited by 1
  15. 2026A3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activationcited by 1
  16. 2026A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Banditscited by 1
  17. 2025MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environmentscited by 0
  18. 2025Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generationcited by 0
  19. 2026Bridging OLAP and RAG: A Multidimensional Approach to the Design of Corpus Partitioningcited by 0
  20. 2026Training-Free Test-Time Contrastive Learning for Large Language Modelscited by 0
  21. 2026RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigmcited by 0
  22. 2026Reinforced Collaboration in Multi-Agent Flow Networkscited by 0
  23. 2026AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomycited by 0
  24. 2026Enhancing Software Engineering Through Closed-Loop Memory Optimizationcited by 0
  25. 2026DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answeringcited by 0
  26. 2026CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
  2. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
  3. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  4. 2025MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
  5. 2024Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference
  6. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
  7. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  8. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models