A survey on large language model based autonomous agents
Обзор автономных агентов на основе больших языковых моделей
2024-03-22
SCID: 54.1/ecy65j47
Discuss with AI
LLM-based autonomous agentsWeb knowledgeagent evaluationautonomous agentslarge language models
Figures from the paper
Abstract (AI)
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 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.
Key Findings
1
It identifies current challenges and outlines future research directions for LLM-based autonomous agents.
2
It proposes a unified framework for constructing LLM-based autonomous agents that encompasses much prior work.
3
LLM-based autonomous agents have been applied across social science, natural science, and engineering domains.
4
The survey summarizes evaluation strategies commonly used to assess LLM-based autonomous agents.
5
The survey systematically reviews research on autonomous agents powered by large language models from a holistic perspective.
Research Object
Large language model (LLM)-based autonomous agents
Research Subject
their construction, applications, evaluation strategies, challenges, and future directions
Publication Details
Publication Date
2024-03-22
Journal
Publisher
ISSN
Cited by
3344
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai17
LLaMA: Open and Efficient Foundation Language Models2023
Proceedings of the 24th international conference on Machine learning2007
A Survey of Large Language Models2026
A Survey on Evaluation of Large Language Models2024
Generative Agents: Interactive Simulacra of Human Behavior2023
GPT-4 Technical Report2023
Evaluating Large Language Models Trained on Code2021
Autonomous chemical research with large language models2023
Can Large Language Models Transform Computational Social Science?2023
Augmenting large language models with chemistry tools2024
Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture2026
ExpeL: LLM Agents Are Experiential Learners2024
AI and the transformation of social science research2023
Can Generative AI improve social science?2024
ChatGPT and Software Testing Education: Promises & Perils2023
ChatMOF: an artificial intelligence system for predicting and generating metal-organic frameworks using large language models2024
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations2025
Cited by20
A Survey of Large Language Models2026
A Comprehensive Overview of Large Language Models2025
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery2024
Unleashing the potential of prompt engineering for large language models2025
A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges2024
AgentClinic: a multimodal benchmark for tool-using clinical AI agents2026
Empowering biomedical discovery with AI agents2024
Visibility into AI Agents2024
Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects2026
Combating misinformation in the age of LLMs: Opportunities and challenges2024
A review of large language models and autonomous agents in chemistry2024
A Survey on Large Language Models for Code Generation2025
Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines2025
The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges2025
Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects2023
Agentic AI: a comprehensive survey of architectures, applications, and future directions2025
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations2025
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents2026
From language to action: a review of large language models as autonomous agents and tool users2026
A Survey on Trustworthy LLM Agents: Threats and Countermeasures2025