arXiv cs.CL· Saroj Mishra, Suman Niroula, Umesh Yadav, Dilip Thakur, Srijan Gyawali, Shiva Gaire·· 11 小时前AI 评分12
arXiv 撤稿：Agentic RAG 系统化综述（SoK）被撤回
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
AI 导读
arXiv Admin 以不符合研究内容质量标准为由撤回了编号 arXiv:2603.07379 的 Agentic RAG 系统化知识（SoK）论文，该文原计划提出首个统一框架，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。
正文 · 原文
This paper has been withdrawn by arXiv Admin
No PDF available, click to view other formats
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.
| Comments: | arXiv admin note: This submission has been withdrawn because it does not meet arXiv's research content quality standards |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2603.07379 [cs.AI] |
| (or arXiv:2603.07379v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2603.07379 arXiv-issued DOI via DataCite |
Submission history
From: arXiv Admin [view email]
[v1]
Sat, 7 Mar 2026 23:38:57 UTC (3,024 KB)
[v2]
Thu, 29 Oct 2026 21:05:01 UTC (1 KB) (withdrawn)
来源：arXiv cs.CL · arxiv.org