Generative and Large AI Models for 6G Wireless Networks: The Optimization Perspective

Yong Zhou; Ting Wang; Youlong Wu; Puyu Cai; Fuhui Zhou; Yuanming Shi

doi:10.1016/j.eng.2026.03.016

Engineering ›› :202603016 DOI: 10.1016/j.eng.2026.03.016

research-article

Generative and Large AI Models for 6G Wireless Networks: The Optimization Perspective

Author information +

History +

PDF (1382KB)

Abstract

The transition to sixth-generation (6G) wireless networks is expected to introduce increasingly complex network architectures, disruptive wireless technologies, ultra-high network density, and diverse service requirements, necessitating highly efficient algorithm design for large-scale and non-convex network optimization. However, conventional optimization-based algorithms usually require sophisticated mathematical modeling and exhibit high computational complexity, while classic learning-based algorithms often suffer from poor robustness and generalization, as well as a lack of cross-scenario meta-optimization capabilities. In contrast, given their strong reasoning and contextual understanding abilities, generative and large artificial intelligence (AI) models are emerging as promising technologies to overcome these limitations. In this article, we propose the leveraging of generative and large AI models for scalable and generalizable network optimization, with an emphasis on facilitating information compression, beamforming design, and automated optimization for dynamic wireless networks with limited radio resources. We introduce a diffusion-based generation framework to solve multi-objective optimization problems for efficient information compression and transmission. We also present a large AI model-based framework for solving non-convex continuous optimization problems for beamforming design in both cell-free wireless networks and integrated sensing and communication networks. Finally, we propose an innovative large AI model-based framework that can automatically solve mixed-integer nonlinear programming problems for microservice deployment over satellite networks.

Keywords

Generative models / Large artificial intelligence models / Sixth-generation wireless networks / Information bottleneck

Cite this article

Download citation ▾

Yong Zhou, Ting Wang, Youlong Wu, Puyu Cai, Fuhui Zhou, Yuanming Shi. Generative and Large AI Models for 6G Wireless Networks: The Optimization Perspective. Engineering 202603016 DOI:10.1016/j.eng.2026.03.016

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Letaief KB , Shi Y , Lu J , Lu J . Edge artificial intelligence for 6G: vision, enabling technologies, and applications. IEEE J Sel Areas Commun 2022; 40(1):5-36.

[2]	M.2160: Framework and overall objectives of the future development of IMT for 2030 and beyond. Geneva: Radio Communication Division of the International Telecommunication Union; 2023.

[3]	Luo ZQ , Yu W . An introduction to convex optimization for communications and signal processing. IEEE J Sel Areas Commun 2006; 24(8):1426-38.

[4]	Shi Y , Lian L , Shi Y , Wang Z , Zhou Y , Fu L , et al. Machine learning for large—scale optimization in 6G wireless networks. IEEE Commun Surv Tutor 2023; 25(4):2088-132.

[5]	Liu YF , Chang TH , Hong M , Wu Z , So AMC , Jorswieck EA , et al. A survey of recent advances in optimization methods for wireless communications. IEEE J Sel Areas Commun 2024; 42(11):2992.

[6]	Zhou Y , Zou Y , Wu Y , Shi Y , Zhang J . Machine learning for low latency communications. London: Elsevier; 2024.

[7]	Tao M , Zhou Y , Shi Y , Lu J , Cui S , Lu J , et al. Federated edge learning for 6G: foundations, methodologies, and applications. Proc IEEE 2025;113(9):1075-113.

[8]	Bommasani R , Hudson DA , Adeli E , Altman R , Arora S , von Arx S , et al. On the opportunities and risks of foundation models. 2021. arXiv:2108.07258.

[9]	Liu Y , Du H , Niyato D , Kang J , Xiong Z , Kim DI , et al. Deep generative model and its applications in efficient wireless network management: a tutorial and case study. IEEE Wirel Commun 2024; 31(4):199-207.

[10]	Wang Z , Shi Y , Zhou Y , Zhu J , Letaief KB . Edge large AI models: revolutionizing 6G networks. IEEE Commun Mag 2025; 63(10):36-42.

[11]	Tishby N , Pereira FC , Bialek W . The information bottleneck method. 2000. arXiv:physics/0004057.

[12]	Xie S, Ma S, Ding M, Shi Y, Tang M, Wu Y. Robust information bottleneck for task—oriented communication with digital modulation. IEEE J Sel Areas Commun 2023; 41(8):2577—91.

[13]	Miettinen K. Nonlinear multiobjective optimization. Boston: Springer; 1999.

[14]	Ho J , Jain AN , Abbeel P . Denoising diffusion probabilistic models. In: Proceedings of the Thirty—Fourth Annual Conference on Neural Information Processing Systems; 2020 Dec 6—12; online.

[15]

Li B , Di Z , Lu Y , Qian H , Wang F , Yang P , et al. Expensive multi—objective Bayesian optimization based on diffusion models In: Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence; 2025 Feb 25—Mar 4; Philadelphia, PA, USA. Association for the Advancement of Artificial Intelligence; 2024. p.27063—71.

[16]	Liu B , Liu X , Gao S , Cheng X , Yang L . LLM4CP: adapting large language models for channel prediction. J Commun Inf Netw 2024; 9(2):113-25.

[17]	Fan S , Liu Z , Gu X , Li H . Csi—LLM: a novel downlink channel prediction method aligned with LLM pre—training. In: Proceedings of IEEE Wireless Communications and Networking Conference; 2025 Mar 24—27; Milan, Italy; New York City: IEEE; 2025.

[18]	Zheng T , Dai L . Large language model enabled multi—task physical layer network. IEEE Trans Commun 2026; 74(1):307-21.

[19]	Wu D , Wang X , Qiao Y , Wang Z , Jiang J , Cui S , et al. NetLLM: adapting large language models for networking. In: Proceedings of ACM SIGCOMM 2024 Conference; 2024 Aug 4—8; Sydney, NSW, Australia. New York City: Association for Computing Machinery; 2024. p. 661—78.

[20]	Wang Z , Zhou Y , Shi Y , Letaief KB . Federated fine—tuning for pre—trained foundation models over wireless networks. IEEE Trans Wirel Commun 2025; 24(4):3450-64.

[21]	Zhao Y , Zhou Y , Wang Z , Shi Y , Cheng N , Zhou H . Learning to beamform for integrated sensing and communication: a graph neural network with implicit projection approach. IEEE Trans Wirel Commun 2025; 24(7):5931-45.

[22]	Chen G , Wang Z , Jia Y , Huang Y , Yang L . An efficient architecture search for scalable beamforming design in cell—free systems. IEEE Trans Veh Technol 2024; 73(7):10241-53.

[23]	Lian L , Bai C , Xu Y , Dong H , Cheng R , Zhang S . Learning to beamform for cooperative localization and communication:a link heterogeneous GNN—based approach. IEEE Trans Wirel Commun 2025; 25:6177-90.

[24]	Abdelsadek MY , Chaudhry AU , Darwish T , Erdogan E , Karabulut—Kurt G , Madoery PG , et al. Future space networks: toward the next giant leap for humankind. IEEE Trans Commun 2023; 71(2):949-1007.

[25]	Shi Y , Zhou Y , Wen D , Wu Y , Jiang C , Letaief KB . Task—oriented communications for 6G: vision, principles, and technologies. IEEE Wirel Commun 2023; 30(3):78-85.

[26]	Goldfeld Z , Polyanskiy Y . The information bottleneck problem and its applications in machine learning. IEEE J Sel Areas Inf Theory 2020;1(1):19-38.

[27]	Yang P , Wen D , Zeng Q , Zhou Y , Wang T , Cai H , et al. Over—the—air computation empowered vertically split inference. IEEE Trans Wirel Commun 2024; 23(12):19634-48.

[28]	Wang Z , Zhao Y , Zhou Y , Shi Y , Jiang C , Letaief KB . Over—the—air computation for 6G: foundations, technologies, and applications. IEEE Internet Things J 2024; 11(14):24634-58.

[29]	Shi Y , Zeng L , Zhu J , Zhou Y , Jiang C , Letaief KB . Satellite federated edge learning: architecture design and convergence analysis. IEEE Trans Wirel Commun 2024; 23(10):15212-29.

[30]	Zhu J , Shi Y , Zhou Y , Jiang C , Kuang L . Hierarchical learning and computing over space—ground integrated networks. IEEE Trans Mobile Comput 2025; 24(10):10423-40.

[31]	Yang P , Wang T , Cai H , Shi Y , Jiang C , Kuang L . Brain—inspired decentralized satellite learning in space computing power networks. IEEE Trans Mobile Comput 2025; 24(12):12935-49.