A survey on large language model based autonomous agents

By Lei Wang, Chengbang Ma, Xueyang Feng, Zeyu Zhang, Hao-ran Yang, Jingsen Zhang, Zhi-Yang Chen, Jiakai Tang, Xu Chen, Yankai Lin and 3 more. Frontiers of Computer Science, 2023

3,361 citations recorded by the source corpus.

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 a 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/28c6ac721f54544162865f41c5692e70d61bccab

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

The rise and potential of large language model based agents: a survey (2025, positive): “Eﬀectively and objectively evaluating LLMs agents presents signiﬁcant challenges, despite their excellent performance in areas such as standalone operation, collective cooperation, and human interaction [70,484].”
Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “Recently, numerous studies have explored language agents which use LLMs for sequential decision-making (Yang et al., 2023; Wang et al., 2023b; Xi et al., 2023; Sumers et al., 2023).”
Why Do Multi-Agent LLM Systems Fail? (2025, neutral): “Recently, Large Language Model (LLM) based agentic systems have gained significant attention in the AI community (Patil et al., 2023; Packer et al., 2024; Wang et al., 2024a).”
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! (2023, background): “The escalating trend of employing LLMs in safety-sensitive cases, including AI agents (Wang et al., 2023a) and financial services (Niszczota & Abbas, 2023), amplifies these threats.”
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks (2024, background): “LLM Agents There has been significant recent interest in using Large Language Models (LLMs) for developing autonomous agents (Xi et al., 2023; Wang et al., 2023a).”
Large Language Models: A Survey (2024, neutral): “Finally, another important area of research we expect to gather increased attention is that of LLM-based agents and multi-agent systems [172], [173], [174].”
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, methodology): “Memory: This ability refers to the capability of LLM-based agent for conducting in-context learning [Dong et al. , 2023a] as short memory or external vector database [Lewis et al. , 2021] as long memory to preserve and retrieve information over prolonged periods [Wang et al. , 2023b].”
A Comprehensive Overview of Large Language Models (2023, neutral): “To study the effects on performance with less data, existing literature [164], [165] finds that the models trained on lesser data can out-perform models trained with more data.”
Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2023, neutral): “Overall, we can flexibly integrate these four parts in the form of natural language text.”
Large language models empowered agent-based modeling and simulation: a survey and perspectives (2023, positive): “Thus, it is promising to construct large language model-empowered agents (Wang et al., 2024b; Xi et al., 2023) due to their human-like intelligence in perceiving the environment and making decisions.”
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (2023, background): “The development of LLM-based agents has made significant progress in the community by endowing LLMs with the ability to perceive surroundings and make decisions individually (Wang et al., 2023a; Yao et al., 2022; Nakajima, 2023; Xie et al., 2023; Zhou et al., 2023).”
Managing extreme AI risks amid rapid progress (2023, background): “However, AI is making progress in critical domains such as hacking, social manipulation, and strategic planning 24,31 , and may soon pose unprecedented con-trol challenges.”
Large language models for generative information extraction: a survey (2023, background): “Furthermore, LLMs can serve as intelligent agents for complex task planning and execution, utilizing memory retrieval and various tools to enhance e ffi ciency and successfully accomplish tasks [23, 24, 25, 26, 27].”
Executable Code Actions Elicit Better LLM Agents (2024, methodology): “Two primary methods for enhancing LLM agents are prompt engineering and instruction tuning, as surveyed by (Wang et al., 2023b).”
Understanding the planning of LLM agents: A survey (2024, methodology): “…to summarize techniques for LLMs [Zhao et al. , 2023a], LLMs for decision-making [Yang et al. , 2023a], reasoning [Sun et al. , 2023], tool learning [Qin et al. , 2023], and autonomous agents [Wang et al. , 2023a], they often lack a detailed analysis of planning ability within the literature.”
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents (2024, background): “Autonomous agents powered by LLMs, known as language agents (Weng, 2023; Sumers et al., 2023), have recently garnered significant attention due to their interactive capabilities (Wang et al., 2023; Sun et al., 2023; Hong et al., 2024a; Durante et al., 2024).”
A Survey on the Memory Mechanism of Large Language Model-based Agents (2024, neutral): “In previous works, the memory contents may come from different sources.”
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair (2024, neutral): “The idea to let LLM agents autonomously plan and perform complex tasks is relatively new and has been applied to tasks outside of software engineering [29].”
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (2023, neutral): “Large language models (LLMs) are becoming a crucial building block in developing powerful agents that utilize LLMs for reasoning, tool usage, and adapting to new observations (Yao et al., 2022; Xi et al., 2023; Wang et al., 2023b) in many real-world tasks.”