迈向深度推理的代理式RAG：大语言模型中RAG推理系统综述

摘要

检索增强生成（RAG）通过引入外部知识提升了大型语言模型（LLMs）的事实准确性，但在需要多步推理的问题上仍显不足；而纯推理导向的方法则常出现事实幻觉或误植。本综述从统一的推理-检索视角综合了这两条研究脉络。首先，我们描绘了高级推理如何优化RAG的各个阶段（推理增强型RAG）。接着，展示了不同类型检索知识如何填补缺失前提并扩展复杂推理的上下文（RAG增强型推理）。最后，聚焦于新兴的协同RAG-推理框架，其中（代理型）LLMs迭代地交替进行搜索与推理，在知识密集型基准测试中达到顶尖性能。我们对方法、数据集及开放挑战进行了分类，并规划了研究路径，旨在开发更高效、多模态适应、可信且以人为本的深层RAG-推理系统。相关资料集可访问https://github.com/DavidZWZ/Awesome-RAG-Reasoning获取。

English

Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). Finally, we spotlight emerging Synergized RAG-Reasoning frameworks, where (agentic) LLMs iteratively interleave search and reasoning to achieve state-of-the-art performance across knowledge-intensive benchmarks. We categorize methods, datasets, and open challenges, and outline research avenues toward deeper RAG-Reasoning systems that are more effective, multimodally-adaptive, trustworthy, and human-centric. The collection is available at https://github.com/DavidZWZ/Awesome-RAG-Reasoning.

迈向深度推理的代理式RAG：大语言模型中RAG推理系统综述

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

摘要

Support