Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects
WIREs Data Mining and Knowledge Discovery · 2026-09 · 16 (3)
DOI: 10.1002/widm.70111 ↗Kurz gefasst
Fachartikel in der Zeitschrift WIREs Data Mining and Knowledge Discovery, online erschienen am 24.07.2026. Verfasst von Yuheng Cheng und 10 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 180 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The concept of the intelligent agent represents a long‐standing pursuit in artificial intelligence. Recent breakthroughs in large language models (LLMs) have catalyzed a paradigm shift, enabling the development of sophisticated agents that exhibit advanced reasoning, planning, and tool‐use capabilities across diverse domains. These LLM‐based agents, which leverage natural language as a universal interface for cognition and interaction, are rapidly advancing from theoretical constructs to practical applications, ranging from autonomous task assistants to complex multi‐agent simulations of social and economic systems. This paper provides an integrative survey of this burgeoning field. We first establish an organizing framework for understanding LLM‐based agents, systematically deconstructing both single‐agent and multi‐agent systems into their core components. We analyze the architectural principles and key mechanisms that underpin their intelligence, including planning paradigms, memory structures, and reflection‐based self‐improvement. We further investigate the dynamics of multi‐agent systems, exploring coordination strategies, communication protocols, and organizational structures. The paper also covers the crucial aspects of performance evaluation, highlighting influential benchmarks and identifying key challenges. Finally, we synthesize the current landscape to discuss the primary challenges, such as the intrinsic limitations of LLMs and the complexities of ensuring safety and alignment, and chart a course for future research directions, including the drive toward continual learning and enhanced multi‐modal capabilities.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cheng, Y., Zhang, C., Zhang, Z., Meng, X., Hong, S., Li, W., Wang, Z., Wang, Z., Yin, F., Zhao, J., & He, X. (2026). Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects. WIREs Data Mining and Knowledge Discovery, 16(3). https://doi.org/10.1002/widm.70111
Vancouver
Cheng Y, Zhang C, Zhang Z, Meng X, Hong S, Li W, et al. Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects. WIREs Data Mining and Knowledge Discovery. 2026;16(3). doi:10.1002/widm.70111
BibTeX
@article{Cheng2026,
author = {Cheng, Yuheng and Zhang, Ceyao and Zhang, Zhengwen and Meng, Xiangrui and Hong, Sirui and Li, Wenhao and Wang, Zihao and Wang, Zekai and Yin, Feng and Zhao, Junhua and He, Xiuqiang},
title = {Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects},
journal = {WIREs Data Mining and Knowledge Discovery},
year = {2026},
volume = {16},
number = {3},
doi = {10.1002/widm.70111}
}
EUVIMED