Cognitive Dialogue: Modular LLM Agents for Context-Aware and Multimodal Customer Service
Academic Conferences Series · 2025-12 · 18 (1)
DOI: 10.62381/acs.dimi2025.10 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academic Conferences Series, 2025-12. Verfasst von Shaojue Yan.
Abstract (Originalsprache)
As companies expand, the need for effective customer service has grown, putting pressure on traditional methods due to rising costs and resource constraints. Shen (2025) explained that recent developments in Artificial Intelligence (AI), particularly with Large Language Models (LLMs), provide promising solutions by offering automated, scalable, and cost-efficient customer support. This paper examines the role of LLMs in intelligent customer service systems, highlighting their ability to hold dynamic conversations, provide multi-language support, and deliver personalized service. By incorporating advanced techniques such as Prompt Engineering and Retrieval-Augmented Generation (RAG), we present a model designed to improve LLM performance, enhancing efficiency, accuracy, and customer satisfaction. Furthermore, we compare the evolution of intelligent customer service systems, contrasting rule-based and deep learning-based models. Our findings suggest that LLM-driven systems can significantly boost service efficiency, lower operational costs, and improve user experiences.
Zitieren
APA
Yan, S. (2025). Cognitive Dialogue: Modular LLM Agents for Context-Aware and Multimodal Customer Service. Academic Conferences Series, 18(1). https://doi.org/10.62381/acs.dimi2025.10
Vancouver
Yan S. Cognitive Dialogue: Modular LLM Agents for Context-Aware and Multimodal Customer Service. Academic Conferences Series. 2025;18(1). doi:10.62381/acs.dimi2025.10
BibTeX
@article{Yan2025,
author = {Yan, Shaojue},
title = {Cognitive Dialogue: Modular LLM Agents for Context-Aware and Multimodal Customer Service},
journal = {Academic Conferences Series},
year = {2025},
volume = {18},
number = {1},
doi = {10.62381/acs.dimi2025.10}
}
EUVIMED