自动化学报2025，Vol.51Issue(6)：1145-1169,25.DOI:10.16383/j.aas.c240163
从RAG到SAGE:现状与展望
From Retrieval-augmented Generation to SAGE:The State of the Art and Prospects
摘要
Abstract
The emergence of large model technologies has significantly enhanced the efficiency with which humans acquire and utilize knowledge.However,in practical applications,they still confront challenges such as constrained knowledge,transfer obstacles,and hallucinations,which impede the construction of trustworthy and reliable artifi-cial intelligence systems.Retrieval-augmented generation(RAG),by leveraging external knowledge bases and query-related retrieval,has effectively strengthened capability of large models and offers strong support for large models to master real-time,industry-specific,and private knowledge,thereby facilitating the rapid promotion and implementa-tion of large model technologies across diverse scenarios.This paper focuses on RAG,detailing its basic principles,current development status,as well as exemplary applications,and analyzing its advantages and the challenges it faces.Based on RAG,we propose the extended framework of search-augmented generation and extension by incor-porating the search module and multi-level cache management module,aiming to create a more flexible and effi-cient knowledge toolchain for large models.关键词
大模型/检索增强生成/基础智能/知识自动化Key words
Large model/retrieval-augmented generation/foundation intelligence/knowledge automation引用本文复制引用
田永林,赵勇,武万森,王飞跃,王雨桐,王兴霞,杨静,沈甜雨,王建功,范丽丽,郭超,王寿文..从RAG到SAGE:现状与展望[J].自动化学报,2025,51(6):1145-1169,25.基金项目
国家自然科学基金青年基金(62303460),澳门特别行政区科学技术发展基金(0145/2023/RIA3),中国科协青年人才托举工程(YESS20220372)资助Supported by National Natural Science Foundation of China(62303460),Science and Technology Development Fund of Ma-cau SAR(0145/2023/RIA3),and Young Elite Scientists Sponsor-ship Program of China Association of Science and Technology(YESS20220372) （62303460）
