Autonomous agents have long been a prominent research topic in the academic community. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from the human learning processes, and thus makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. This has sparked an upsurge in studies investigating autonomous agents based on LLMs. To harness the full potential of LLMs, researchers have devised diverse agent architectures tailored to different applications. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of autonomous agents from a holistic perspective. More specifically, our focus lies in the construction of LLM-based agents, for which we propose a unified framework that encompasses a majority of the previous work. Additionally, we provide a summary of the various applications of LLM-based AI agents in the domains of social science, natural science, and engineering. Lastly, we discuss the commonly employed evaluation strategies for LLM-based AI agents. Based on the previous studies, we also present several challenges and future directions in this field. To keep track of this field and continuously update our survey, we maintain a repository for the related references at https://github.com/Paitesanshi/LLM-Agent-Survey.

翻译：自主智能体长期以来一直是学术界的热点研究方向。以往该领域的研究通常侧重于在隔离环境中训练知识有限的智能体，这与人类的学习过程存在显著差异，从而难以实现类人决策。近年来，通过获取海量网络知识，大型语言模型（LLM）在实现人类级智能方面展现出卓越潜力，这引发了基于LLM的自主智能体研究热潮。为充分发挥LLM的潜能，研究者针对不同应用场景设计了多样化的智能体架构。本文系统梳理了这些研究，从整体视角对自主智能体领域进行了全面综述。具体而言，我们聚焦于LLM驱动智能体的构建，提出一个涵盖大部分先前研究的统一框架。同时，我们总结了基于LLM的AI智能体在社会科学、自然科学和工程领域中的各类应用，并探讨了常用的评估策略。基于现有研究，我们还指出了该领域面临的挑战与未来发展方向。为持续追踪领域进展并更新综述，我们在https://github.com/Paitesanshi/LLM-Agent-Survey维护了相关参考文献库。