EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Collaborative Large–Small AI Models for 6G

Yongming Huang, Hang Zhan, Haihang Jiang, Jingyi Chen, Jiaheng Wang

IEEE Journal on Selected Areas in Communications · 2026 · 44 · 2574-2590

DOI: 10.1109/jsac.2025.3643414 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2026. Verfasst von Yongming Huang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu, Science and Technology Major Project of Jiangsu.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sixth-Generation (6G) networks necessitate intelligent and energy-efficient operations. However, the direct deployment of Large Language Models (LLMs) for real-time 6G control is hindered by significant latency and energy constraints, conflicting with green 6G imperatives. This paper pioneers a collaborative architecture of large-small AI models to address these challenges. In this architecture, resource-intensive LLMs, i.e., large models, are strategically employed offline for comprehensive Wireless Data Knowledge Graph (WDKG) construction, effectively distilling domain knowledge. This WDKG, in turn, enables the development and deployment of lightweight, efficient small models for real-time network tasks by facilitating the generation of optimized feature datasets. To operationalize this, we first introduce a novel multi-agent collaborative LLM framework, bolstered by an enhanced semantic representation method incorporating domain-adaptive embedding fine-tuning and mutual information (MI)-based feature encoding, for automated high-fidelity WDKG construction. Subsequently, we propose the Semantic-Data and Spatio-Temporal (SD-ST) model, which uniquely fuses LLM-extracted semantic information with the spatio-temporal characteristics of wireless network data and WDKG structure. Insights from the SD-ST model guide a WDKG-driven method for generating optimized feature datasets by evaluating node influence and redundancy. Experimental validation demonstrates that these distilled feature datasets lead to substantial reductions in training and inference overhead for the lightweight downstream AI models, offering a tangible pathway towards greener, more efficient, and intelligent 6G networks.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu
  • Science and Technology Major Project of Jiangsu

Zitieren

APA

Huang, Y., Zhan, H., Jiang, H., Chen, J., & Wang, J. (2026). Collaborative Large–Small AI Models for 6G. IEEE Journal on Selected Areas in Communications, 44, 2574-2590. https://doi.org/10.1109/jsac.2025.3643414

Vancouver

Huang Y, Zhan H, Jiang H, Chen J, Wang J. Collaborative Large–Small AI Models for 6G. IEEE Journal on Selected Areas in Communications. 2026;44:2574-2590. doi:10.1109/jsac.2025.3643414

BibTeX
@article{Huang2026,
  author = {Huang, Yongming and Zhan, Hang and Jiang, Haihang and Chen, Jingyi and Wang, Jiaheng},
  title = {Collaborative Large–Small AI Models for 6G},
  journal = {IEEE Journal on Selected Areas in Communications},
  year = {2026},
  volume = {44},
  pages = {2574--2590},
  doi = {10.1109/jsac.2025.3643414}
}
Kostenlos starten →