Large Language Model-Empowered Wireless Networks: Fundamentals, Architecture, and Challenges
| dc.contributor.author | Khan, Latif U. | |
| dc.contributor.author | Guizani, Maher | |
| dc.contributor.author | Muhaidat, Sami | |
| dc.contributor.author | Hong, Choong Seon | |
| dc.date.accessioned | 2026-08-25T06:21:05Z | |
| dc.date.issued | 2026-02-03 | |
| dc.description | In the upcoming years, we will witness novel applications (e.g., metaverse and holographic applications, i.e., healthcare, intelligent transportation systems, brain-computer interaction, and industry 5.0, among others) that will be very difficult to enable using the existing wireless systems [1]. Therefore, we will need a transition from traditional architecture to novel architecture/s. This transition is due to the novel’s diverse requirements (e.g., metaverse with human-like decisions and semantic communication with logical reasoning abilities) for novel use cases. Therefore, for effective enabling of such kinds of applications, there is a need for a novel system design that follows new design trends. Mainly, these design trends are self-organizing and proactive analytics. | |
| dc.description.abstract | The rapid advancement of wireless networks has resulted in numerous challenges stemming from their extensive demands for quality of service towards innovative quality of experience metrics (e.g., user-defined metrics in terms of sense of physical experience for haptics applications). In the meantime, large language models (LLMs) emerged as promising solutions for many difficult and complex applications/tasks. These lead to a notion of the integration of LLMs and wireless networks. However, this integration is challenging and needs careful attention in design. Therefore, in this article, we present a notion of rational wireless networks powered by telecom LLMs, namely, LLM-native wireless systems. We provide fundamentals, a vision, and a case study of a distributed implementation of LLM-native wireless systems. In the case study, we propose a solution based on double deep Q-learning (DDQN) that outperforms existing DDQN solutions. Finally, we provide open challenges. Keywords Internet of Things, large language models, deep reinforcement learning, convex optimization | |
| dc.identifier.citation | Khan, L. U., Guizani, M., Muhaidat, S., & Hong, C. S. (2026). Large Language Model-Empowered Wireless Networks: Fundamentals, Architecture, and Challenges. IEEE Internet of Things Magazine. | |
| dc.identifier.doi | https://doi.org/10.1109/MIOT.2025.3645155 | |
| dc.identifier.uri | https://repository.adu.ac.ae/handle/1/8463 | |
| dc.language.iso | en | |
| dc.publisher | IEEE | |
| dc.title | Large Language Model-Empowered Wireless Networks: Fundamentals, Architecture, and Challenges | |
| dc.type | Article |