梳理推理型智能检索生成系统，解决工业场景复杂问题
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
- 区分预设流程与自主决策两种推理范式
- 总结架构设计与工具协同的关键技术方法
- 适合研究AI推理与检索融合的从业者参考
检索增强生成（RAG）通过整合外部检索与语言生成，克服大模型的知识局限。早期基于静态流水线的RAG在结构化任务中有效，但在需要复杂推理、动态检索和多模态融合的真实场景中表现不足。为此，领域转向推理型智能体RAG，将决策与自适应工具使用嵌入检索过程。本文全面综述该方向，将其分为两类：预设推理（固定模块化流程提升推理能力）与智能体推理（模型在推理中自主协调工具交互）。分析代表性技术，涵盖架构设计、推理策略与工具协同机制。最后讨论关键挑战并提出未来方向，以提升系统的灵活性、鲁棒性与实用性。相关研究已整理至 https://github.com/ByebyeMonica/Reasoning-Agentic-RAG。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG systems based on static pipelines have shown effectiveness in well-structured tasks, they struggle in real-world scenarios requiring complex reasoning, dynamic retrieval, and multi-modal integration. To address these challenges, the field has shifted toward Reasoning Agentic RAG, a paradigm that embeds decision-making and adaptive tool use directly into the retrieval process. In this paper, we present a comprehensive review of Reasoning Agentic RAG methods, categorizing them into two primary systems: predefined reasoning, which follows fixed modular pipelines to boost reasoning, and agentic reasoning, where the model autonomously orchestrates tool interaction during inference. We analyze representative techniques under both paradigms, covering architectural design, reasoning strategies, and tool coordination. Finally, we discuss key research challenges and propose future directions to advance the flexibility, robustness, and applicability of reasoning agentic RAG systems. Our collection of the relevant research has been organized into a https://github.com/ByebyeMonica/Reasoning-Agentic-RAG.
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。