摘要
在人工智能飞速发展的背景下,基于大语言模型的智能体构建已成为当前的研究热点。基于大语言模型的智能体主要以大语言模型为核心,通过任务规划和决策,完成复杂任务的执行。围绕大语言模型智能体的国内外研究现状进行系统综述,介绍了当前主流技术及实现方法,从智能体分类和基本组成对典型智能体的结构进行详细介绍,引入典型智能体案例为基于大语言模型的智能体研究提供思路,详细介绍了智能体有效性评估方法,并对未来的研究方向进行了探讨与展望。
Against the backdrop of rapid development of artificial intelligence,the construction of intelligent agents based on large language models becomes a current research hotspot.Intelligent agents based on large language models mainly use large language models as the core to accomplish the execution of complex tasks through task planning and decision making.This paper presents a systematic review of the current state of research on intelligent agent base on large language models at home and abroad,introduces the current mainstream technologies and implementation methods,and provides a detailed introduction to the structure of typical intelligent agents from the perspectives of intelligent agent classification and basic composition of intelligent agent.This paper introduces a typical intelligent agent case,provides ideas for the research of intelligent agents based on large language models,introduces in detail the method of evaluating the validity of intelligent agents,and discusses and looks forward to the future research directions.
作者
郭先会
张梦姣
马军
GUO Xianhui;ZHANG Mengjiao;MA Jun(Shenzhen CyberAray Network Technology Co.,Ltd.,Shenzhen Guangdong 518042,China;Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Technology Research Center.,Chengdu Sichuan 610059,China)
出处
《通信技术》
2024年第9期873-879,共7页
Communications Technology
关键词
大语言模型
智能体
任务规划
任务执行
large language model
intelligent agent
task planning
task execution