Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
IEEE Transactions on Neural Networks and Learning Systems · 2025-06 · 36 (6) · 9737-9757
DOI: 10.1109/tnnls.2024.3497992 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2025-06. Verfasst von Yuji Cao und 9 weiteren Autor:innen. Die Arbeit wurde bisher 180-mal zitiert (Crossref) und nennt 187 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Power Grid Company, Shenzhen Key Lab of Crowd Intelligence Empowered Low-Carbon Energy Network.
Abstract (Originalsprache)
With extensive pretrained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects, such as multitask learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared with conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs' functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated and provide insights into future directions. Finally, the comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications, such as robotics, autonomous driving, and energy systems.
Förderung
- National Natural Science Foundation of China
- Guangdong Power Grid Company
- Shenzhen Key Lab of Crowd Intelligence Empowered Low-Carbon Energy Network
- Shenzhen Natural Science Fund
- Shenzhen Institute of Artificial Intelligence and Robotics for Society
- PolyU Direct Grant
- CUHK Strategic Partnership Award for Research Collaboration
- CUHK Direct Grant for Research
Zitieren
APA
Cao, Y., Zhao, H., Cheng, Y., Shu, T., Chen, Y., Liu, G., Liang, G., Zhao, J., Yan, J., & Li, Y. (2025). Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods. IEEE Transactions on Neural Networks and Learning Systems, 36(6), 9737-9757. https://doi.org/10.1109/tnnls.2024.3497992
Vancouver
Cao Y, Zhao H, Cheng Y, Shu T, Chen Y, Liu G, et al. Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods. IEEE Transactions on Neural Networks and Learning Systems. 2025;36(6):9737-9757. doi:10.1109/tnnls.2024.3497992
BibTeX
@article{Cao2025,
author = {Cao, Yuji and Zhao, Huan and Cheng, Yuheng and Shu, Ting and Chen, Yue and Liu, Guolong and Liang, Gaoqi and Zhao, Junhua and Yan, Jinyue and Li, Yun},
title = {Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2025},
volume = {36},
number = {6},
pages = {9737--9757},
doi = {10.1109/tnnls.2024.3497992}
}
EUVIMED