SoK：基于代理的检索增强生成（RAG）：分类、架构、评估及研究方向
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
AI总结：
本文系统化地分析了基于代理的RAG系统，提出统一框架，识别关键风险并提出研究方向，以构建可靠可扩展的自主检索生成系统。
摘要：
检索增强生成（RAG）系统正逐渐发展为具有代理架构的系统，其中大型语言模型能够自主协调多步骤推理、动态内存管理和迭代检索策略。尽管在工业界迅速普及，但目前的研究缺乏对基于代理的RAG作为顺序决策系统的系统性理解，导致架构碎片化、评估方法不一致以及可靠性风险未解决。本系统化知识（SoK）论文提供了理解这些自主系统的首个统一框架。我们正式将基于代理的检索生成循环定义为有限时间 horizon 的部分可观测马尔可夫决策过程，明确建模其控制策略和状态转移。在此基础上，我们开发了全面的分类和模块化架构分解，按规划机制、检索协调、内存范式和工具调用行为对系统进行分类。我们进一步分析了传统静态评估实践的关键局限，并识别了自主循环中固有的严重系统风险，包括叠加幻觉传播、内存污染、检索偏差以及工具执行漏洞的级联效应。最后，我们概述了关键博士级研究方向，涵盖稳定适应性检索、成本感知协调、形式轨迹评估和监督机制，为构建可靠、可控和可扩展的基于代理的检索系统提供了明确路线图。
英文摘要：
Retrieval-Augmented Generation (RAG) systems are increasingly evolving into agentic architectures where large language models autonomously coordinate multi-step reasoning, dynamic memory management, and iterative retrieval strategies. Despite rapid industrial adoption, current research lacks a systematic understanding of Agentic RAG as a sequential decision-making system, leading to highly fragmented architectures, inconsistent evaluation methodologies, and unresolved reliability risks. This Systematization of Knowledge (SoK) paper provides the first unified framework for understanding these autonomous systems. We formalize agentic retrieval-generation loops as finite-horizon partially observable Markov decision processes, explicitly modeling their control policies and state transitions. Building upon this formalization, we develop a comprehensive taxonomy and modular architectural decomposition that categorizes systems by their planning mechanisms, retrieval orchestration, memory paradigms, and tool-invocation behaviors. We further analyze the critical limitations of traditional static evaluation practices and identify severe systemic risks inherent to autonomous loops, including compounding hallucination propagation, memory poisoning, retrieval misalignment, and cascading tool-execution vulnerabilities. Finally, we outline key doctoral-scale research directions spanning stable adaptive retrieval, cost-aware orchestration, formal trajectory evaluation, and oversight mechanisms, providing a definitive roadmap for building reliable, controllable, and scalable agentic retrieval systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
