系统梳理RAG架构与信任框架，助力构建可靠知识增强模型。
Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems
- 构建统一分类体系，整合多样化的RAG融合与检索方法。
- 提出量化评估框架，分析信任与对齐机制在实际部署中的影响。
- 适合研发人员、系统架构师及关注RAG可信部署的实践者。
本文从2018年至2025年间学术研究、工业应用和真实部署中，系统回顾了检索增强生成（RAG）技术的发展。RAG通过引入外部知识，在不增加大模型容量的前提下实现知识更新与扩展。随着方法多样性加剧，研究与工程实践逐渐碎片化，涵盖多种融合机制、检索策略与调度方式。本文提出量化评估框架，分析其对信任与对齐的影响，并将现有RAG技术系统性地归纳为统一分类体系。该文档为构建稳健、安全且可领域适配的RAG系统提供实用指南，综合了学术文献、行业报告与技术实现资料，亦可作为技术参考手册。
原文摘要 · Abstract (English)
This article provides a comprehensive systematic literature review of academic studies, industrial applications, and real-world deployments from 2018 to 2025, providing a practical guide and detailed overview of modern Retrieval-Augmented Generation (RAG) architectures. RAG offers a modular approach for integrating external knowledge without increasing the capacity of the model as LLM systems expand. Research and engineering practices have been fragmented as a result of the increasing diversity of RAG methodologies, which encompasses a variety of fusion mechanisms, retrieval strategies, and orchestration approaches. We provide quantitative assessment frameworks, analyze the implications for trust and alignment, and systematically consolidate existing RAG techniques into a unified taxonomy. This document is a practical framework for the deployment of resilient, secure, and domain-adaptable RAG systems, synthesizing insights from academic literature, industry reports, and technical implementation guides. It also functions as a technical reference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。