cs.AI提交于 2026-11-02已译

SoK: 智能体检索增强生成（RAG）：分类体系、架构、评估与研究方向

SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions

Saroj Mishra · Suman Niroula · Umesh Yadav · Dilip Thakur · Srijan Gyawali · Shiva Gaire

中文摘要

检索增强生成（RAG）系统正日益演化为智能体架构，由大语言模型自主协调多步推理、动态内存管理与迭代检索策略。尽管工业界采用迅速，当前研究仍缺乏将智能体 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未解。本系统化知识（SoK）论文首次提供理解这些自主系统的统一框架。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，构建全面的分类体系与模块化架构分解，按规划机制、检索编排、内存范式与工具调用行为对系统分类。进一步分析传统静态评估实践的关键局限，识别自主循环固有的严重系统性风险，包括复合幻觉传播、内存投毒、检索错位与级联工具执行漏洞。最后，概述博士级重点研究方向，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，为构建可靠、可控且可扩展的智能体检索系统提供明确路线图。

关键要点

01将智能体 RAG 形式化为有限时域部分可观测马尔可夫决策过程，显式建模控制策略与状态转移。
02提出按规划机制、检索编排、内存范式与工具调用行为分类的模块化架构分解。
03指出现有静态评估方法的局限，并识别复合幻觉传播、内存投毒、检索错位与级联工具执行漏洞等系统性风险。
04给出稳定自适应检索、成本感知编排、形式化轨迹评估与监督机制等博士级研究方向。

解读

尚无解读。

原始英文摘要

arXiv:2603.07379v2 Announce Type: replace-cross Abstract: 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.