A Survey on Large Language Model based Autonomous Agents
Lei Wang Chen Ma111Both authors contribute equally to this paper. Xueyang Feng111Both authors contribute equally to this paper. Zeyu Zhang Hao Yang Jingsen Zhang Zhi-Yuan Chen Jiakai Tang Wayne Xin Zhao Zhewei Wei Ji-Rong Wen Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, 100872, China
Abstract
Autonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have shown potential in human-level intelligence, leading to a surge in research on LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of LLM-based autonomous agents from a holistic perspective. We first discuss the construction of LLM-based autonomous agents, proposing a unified framework that encompasses much of previous work. Then, we present an overview of the diverse applications of LLM-based autonomous agents in social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field.
中文速览
让大语言模型（LLM）真正像人一样自主完成复杂任务，一直是人工智能领域的核心挑战。这篇综述系统梳理了以LLM为核心控制器的自主智能体（LLM-based autonomous agents）的最新进展，提出了一个统一框架，将智能体的构建拆解为"画像模块、记忆模块、规划模块、行动模块"四大组件，并从社会科学、自然科学和工程应用三个领域全面盘点了这类智能体的实际落地场景，同时归纳了主观与客观两类评估策略。研究发现，相比传统强化学习智能体，LLM驱动的智能体天然携带海量世界知识，能够在无需特定领域训练数据的情况下做出接近人类水准的决策，并支持自然语言交互与可解释推理。这项工作为新入门的研究者提供了系统性的知识地图，也为推动该领域突破性研究指明了若干关键挑战与未来方向。
原文 arXiv:2308.11432;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2308.11432v7