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.

翻译：检索增强生成（RAG）系统正日益演化为智能体架构，其中大型语言模型能够自主协调多步推理、动态内存管理与迭代检索策略。尽管工业界应用迅速，当前研究仍缺乏对智能体RAG作为序列决策系统的系统性理解，导致架构高度碎片化、评估方法不一致以及可靠性风险悬而未决。本文作为知识系统化综述，首次提出了理解这类自主系统的统一框架。我们将智能体检索-生成循环形式化为有限时域部分可观测马尔可夫决策过程，显式建模其控制策略与状态转移。基于此形式化框架，我们建立了涵盖规划机制、检索编排、内存范式及工具调用行为的综合分类体系与模块化架构解构。我们进一步剖析了传统静态评估方法的关键局限，并揭示了自主循环固有的严重系统性风险，包括复合幻觉传播、内存污染、检索失准以及级联工具执行漏洞。最后，我们规划了涵盖稳定自适应检索、成本感知编排、形式化轨迹评估与监督机制等关键博士层级的研究方向，为构建可靠、可控且可扩展的智能体检索系统提供了明确的路线图。