迈向具深度推理能力的代理式RAG：大语言模型中RAG推理系统综述

摘要

檢索增強生成（RAG）通過注入外部知識提升了大型語言模型（LLM）的事實準確性，但在需要多步推理的問題上仍顯不足；相反，純粹以推理為導向的方法往往會產生幻覺或錯誤地錨定事實。本綜述從統一的推理-檢索視角綜合了這兩種思路。我們首先探討了高級推理如何優化RAG的各個階段（推理增強型RAG）。接著，展示了不同類型的檢索知識如何為複雜推理提供缺失的前提並擴展上下文（RAG增強型推理）。最後，聚焦於新興的RAG-推理協同框架，其中（具代理性的）LLM迭代地交織搜索與推理，在知識密集型基準測試中實現了頂尖性能。我們對方法、數據集及開放性挑戰進行了分類，並勾勒出研究路徑，旨在構建更有效、多模態適應性更強、更可信且以人為本的深度RAG-推理系統。該資源集可在https://github.com/DavidZWZ/Awesome-RAG-Reasoning 獲取。

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.

迈向具深度推理能力的代理式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