LARGE MODEL AGENTS: A SURVEY ON TECHNICAL EVOLUTION, MULTIMODAL FUSION, AND VERTICAL DOMAIN APPLICATIONS
Journal of Trends in Applied Science and Advanced Technologies · 2026
DOI: 10.61784/asat3023 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Trends in Applied Science and Advanced Technologies, 2026. Verfasst von ShouTong Huang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
LLM-driven agent technology has achieved breakthrough progress, marking AI's leap from perceptual to actionable intelligence. This paper reviews four evolution stages: symbolic, reactive, RL, and LLM-driven agents. It analyzes core architecture including ReAct, memory, tool calling, and multimodal perception. For education and healthcare, we design a GLM-4-based multimodal educational assistant and a ReAct-based MedGuard medication assistant, validating effectiveness through experiments. Finally, we analyze six challenges (hallucination, alignment, security, planning, cost, interpretability) and propose directions: world models, RL fine-tuning, verifiable execution, edge deployment, and ethical frameworks.
Zitieren
APA
Huang, S., Ma, Y., Ding, T., & Ma, R. (2026). LARGE MODEL AGENTS: A SURVEY ON TECHNICAL EVOLUTION, MULTIMODAL FUSION, AND VERTICAL DOMAIN APPLICATIONS. Journal of Trends in Applied Science and Advanced Technologies. https://doi.org/10.61784/asat3023
Vancouver
Huang S, Ma Y, Ding T, Ma R. LARGE MODEL AGENTS: A SURVEY ON TECHNICAL EVOLUTION, MULTIMODAL FUSION, AND VERTICAL DOMAIN APPLICATIONS. Journal of Trends in Applied Science and Advanced Technologies. 2026. doi:10.61784/asat3023
BibTeX
@article{Huang2026,
author = {Huang, ShouTong and Ma, Yu and Ding, Tong and Ma, Rui},
title = {LARGE MODEL AGENTS: A SURVEY ON TECHNICAL EVOLUTION, MULTIMODAL FUSION, AND VERTICAL DOMAIN APPLICATIONS},
journal = {Journal of Trends in Applied Science and Advanced Technologies},
year = {2026},
doi = {10.61784/asat3023}
}
EUVIMED