Large Language Models (LLMs) demonstrate significant capabilities but face challenges such as hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Augmented Generation (RAG) has emerged as a promising solution to these issues by incorporating real-time data from external databases into LLM responses. This enhances the accuracy and credibility of the models, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This survey paper provides an in-depth analysis of the evolution of RAG, focusing on three key paradigms: Naive RAG, Advanced RAG, and Modular RAG. It methodically examines the three fundamental components of RAG systems: the retriever, the generator, and the augmentation methods, underscoring the cutting-edge technologies within each componenet. Additionally, the paper introduces novel metrics and capabilities for evaluating RAG models, as well as the most recent evaluation framework. Finally, the paper outlines future research directions from three perspectives: future challenges,modality extension,and the development of the RAG technical stack and ecosystem

翻译：大语言模型（LLMs）展现出显著能力，但面临幻觉、知识过时以及推理过程不透明、不可追溯等挑战。检索增强生成（RAG）通过将外部数据库的实时数据融入LLM响应，已成为解决这些问题的有效方案。该方法提升了模型在知识密集型任务中的准确性与可信度，并支持持续知识更新和领域特定信息整合。RAG协同融合了LLMs的内在知识与外部数据库的庞大数据资源。本综述论文深入分析了RAG的发展历程，聚焦三种关键范式：朴素RAG、先进RAG与模块化RAG。文章系统性地考察了RAG系统的三大核心组件——检索器、生成器及增强方法，重点阐述了各组件中的前沿技术。此外，本文介绍了评估RAG模型的新颖指标与能力标准，以及最新的评估框架。最后，论文从未来挑战、模态扩展、RAG技术栈与生态系统发展三个维度，展望了未来研究方向。