Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2501.15228v2
• Date: Tue, 07 Oct 2025 04:38:36 GMT
• Title: Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
• Authors: Yiqun Chen, Lingyong Yan, Weiwei Sun, Xinyu Ma, Yi Zhang, Shuaiqiang Wang, Dawei Yin, Yiming Yang, Jiaxin Mao,
• Abstract summary: Retrieval-augmented generation (RAG) is widely utilized to incorporate external knowledge into large language models.<n>A standard RAG pipeline consists of several components, such as query rewriting, document retrieval, document filtering, and answer generation.<n>We propose treating the complex RAG pipeline with multiple components as a multi-agent cooperative task, in which each component can be regarded as an RL agent.
• Score: 88.55095746156428
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented generation (RAG) is widely utilized to incorporate external knowledge into large language models, thereby enhancing factuality and reducing hallucinations in question-answering (QA) tasks. A standard RAG pipeline consists of several components, such as query rewriting, document retrieval, document filtering, and answer generation. However, these components are typically optimized separately through supervised fine-tuning, which can lead to misalignments between the objectives of individual components and the overarching aim of generating accurate answers. Although recent efforts have explored using reinforcement learning (RL) to optimize specific RAG components, these approaches often focus on simple pipelines with only two components or do not adequately address the complex interdependencies and collaborative interactions among the modules. To overcome these limitations, we propose treating the complex RAG pipeline with multiple components as a multi-agent cooperative task, in which each component can be regarded as an RL agent. Specifically, we present MMOA-RAG, Multi-Module joint Optimization Algorithm for RAG, which employs multi-agent reinforcement learning to harmonize all agents' goals toward a unified reward, such as the F1 score of the final answer. Experiments conducted on various QA benchmarks demonstrate that MMOA-RAG effectively boost the overall performance of the pipeline and outperforms existing baselines. Furthermore, comprehensive ablation studies validate the contributions of individual components and demonstrate MMOA-RAG can be adapted to different RAG pipelines and benchmarks.

Related papers

• Integrating Diverse Assignment Strategies into DETRs [61.61489761918158]
  Label assignment is a critical component in object detectors, particularly within DETR-style frameworks.<n>We propose LoRA-DETR, a flexible and lightweight framework that seamlessly integrates diverse assignment strategies into any DETR-style detector.
  arXiv  Detail & Related papers  (2026-01-14T07:28:54Z)
• Is Agentic RAG worth it? An experimental comparison of RAG approaches [0.07777489763207261]
  "Retrieval-Augmented Generation" systems are usually defined by the combination of a generator and a retrieval component.<n>These shortcomings have motivated the development of "Enhanced" RAG.<n>The growing self-reflective capabilities of Large Language Models have enabled a new paradigm, which we refer to as "Agentic" RAG.
  arXiv  Detail & Related papers  (2026-01-12T16:43:44Z)
• MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval [50.30107119622642]
  Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data.<n>Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge.<n>MarAG-R1 is a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms.
  arXiv  Detail & Related papers  (2025-10-31T15:51:39Z)
• Domain-Specific Data Generation Framework for RAG Adaptation [58.20906914537952]
  Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models with external retrieval to enable domain-grounded responses.<n>We propose RAGen, a framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches.
  arXiv  Detail & Related papers  (2025-10-13T09:59:49Z)
• SIRAG: Towards Stable and Interpretable RAG with A Process-Supervised Multi-Agent Framework [7.37561751991963]
  We propose a process-supervised multi-agent framework to bridge the gap between retriever and generator.<n>The proposed framework is modular and plug-and-play, requiring no modification to the retriever or generator.
  arXiv  Detail & Related papers  (2025-09-17T09:09:28Z)
• MSRS: Evaluating Multi-Source Retrieval-Augmented Generation [51.717139132190574]
  Many real-world applications demand the ability to integrate and summarize information scattered across multiple sources.<n>We present a scalable framework for constructing evaluation benchmarks that challenge RAG systems to integrate information across distinct sources.
  arXiv  Detail & Related papers  (2025-08-28T14:59:55Z)
• UR$^2$: Unify RAG and Reasoning through Reinforcement Learning [17.319590573147565]
  Large Language Models (LLMs) have shown remarkable capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) and Reinforcement Learning from Verifiable Rewards (RLVR)<n>We propose UR2 (Unified RAG and Reasoning), a general framework that unifies retrieval and reasoning through reinforcement learning.<n>Experiments across open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks demonstrate that UR$2$ significantly outperforms existing RAG and RL methods.
  arXiv  Detail & Related papers  (2025-08-08T09:33:20Z)
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory [57.449129198822476]
  RCR is a role-aware context routing framework for multi-agent large language model (LLM) systems.<n>It dynamically selects semantically relevant memory subsets for each agent based on its role and task stage.<n>A lightweight scoring policy guides memory selection, and agent outputs are integrated into a shared memory store.
  arXiv  Detail & Related papers  (2025-08-06T21:59:34Z)
• MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation [35.853052535353775]
  In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues.<n>We propose an adaptive RAG framework called MAO-ARAG, which leverages multi-agent orchestration.
  arXiv  Detail & Related papers  (2025-08-01T18:15:22Z)
• MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning [43.66966457772646]
  MA-RAG orchestrates a collaborative set of specialized AI agents to tackle each stage of the RAG pipeline with task-aware reasoning.<n>Our design allows fine-grained control over information flow without any model fine-tuning.<n>This modular and reasoning-driven architecture enables MA-RAG to deliver robust, interpretable results.
  arXiv  Detail & Related papers  (2025-05-26T15:05:18Z)
• UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities [53.76854299076118]
  UniversalRAG is a novel RAG framework designed to retrieve and integrate knowledge from heterogeneous sources with diverse modalities and granularities. We propose a modality-aware routing mechanism that dynamically identifies the most appropriate modality-specific corpus and performs targeted retrieval within it. We validate UniversalRAG on 8 benchmarks spanning multiple modalities, showing its superiority over modality-specific and unified baselines.
  arXiv  Detail & Related papers  (2025-04-29T13:18:58Z)
• HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation [11.53083922927901]
  HM-RAG is a novel Hierarchical Multi-agent Multimodal RAG framework. It pioneers collaborative intelligence for dynamic knowledge synthesis across structured, unstructured, and graph-based data.
  arXiv  Detail & Related papers  (2025-04-13T06:55:33Z)
• C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation [13.120930059424975]
  C-3PO is a proxy-centric framework that facilitates communication between retrievers and large language models. Our framework implements three specialized agents that collaboratively optimize the entire RAG pipeline.
  arXiv  Detail & Related papers  (2025-02-10T07:04:32Z)
• Talk to Right Specialists: Routing and Planning in Multi-agent System for Question Answering [47.29580414645626]
  RopMura is a novel multi-agent system that integrates multiple knowledge bases into a unified RAG-based agent.<n>RopMura features two key components: a router that intelligently selects the most relevant agents based on knowledge boundaries and a planner that decomposes complex multi-hop queries into manageable steps.
  arXiv  Detail & Related papers  (2025-01-14T03:25:26Z)
• MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation [34.66546005629471]
  Large Language Models (LLMs) are essential tools for various natural language processing tasks but often suffer from generating outdated or incorrect information.<n>Retrieval-Augmented Generation (RAG) addresses this issue by incorporating external, real-time information retrieval to ground LLM responses.<n>To tackle this problem, we propose Multi-Agent Filtering Retrieval-Augmented Generation (MAIN-RAG)<n>MAIN-RAG is a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents.
  arXiv  Detail & Related papers  (2024-12-31T08:07:26Z)
• XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation [37.78210992036775]
  Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs)<n>We introduce XRAG, an open-source, modular that facilitates exhaustive evaluation of the performance of foundational components of advanced RAG modules.
  arXiv  Detail & Related papers  (2024-12-20T03:37:07Z)
• mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA [78.45521005703958]
  multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge. We propose a novel framework called textbfRetrieval-textbfReftextbfAugmented textbfGeneration (mR$2$AG) which achieves adaptive retrieval and useful information localization. mR$2$AG significantly outperforms state-of-the-art MLLMs on INFOSEEK and Encyclopedic-VQA
  arXiv  Detail & Related papers  (2024-11-22T16:15:50Z)
• Multi-Head RAG: Solving Multi-Aspect Problems with LLMs [13.638439488923671]
  Retrieval Augmented Generation (RAG) enhances the abilities of Large Language Models (LLMs) Existing RAG solutions do not focus on queries that may require fetching multiple documents with substantially different contents. This paper introduces Multi-Head RAG (MRAG), a novel scheme designed to address this gap with a simple yet powerful idea.
  arXiv  Detail & Related papers  (2024-06-07T16:59:38Z)
• FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research [70.6584488911715]
  retrieval-augmented generation (RAG) has attracted considerable research attention. Existing RAG toolkits are often heavy and inflexibly, failing to meet the customization needs of researchers. Our toolkit has implemented 16 advanced RAG methods and gathered and organized 38 benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-22T12:12:40Z)
• CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models [49.16989035566899]
  Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios.
  arXiv  Detail & Related papers  (2024-01-30T14:25:32Z)
• Plug-and-Play Regulators for Image-Text Matching [76.28522712930668]
  Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching. We develop two simple but quite effective regulators which efficiently encode the message output to automatically contextualize and aggregate cross-modal representations. Experiments on MSCOCO and Flickr30K datasets validate that they can bring an impressive and consistent R@1 gain on multiple models.
  arXiv  Detail & Related papers  (2023-03-23T15:42:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.