Workshop on Foundation Models, Generative AI, and Agentic Intelligence for AI-Native Radio Access Networks (AI-RAN)
Workshop on Foundation Models, Generative AI, and Agentic Intelligence for AI-Native Radio Access Networks (AI-RAN)
Scope of the Workshop
Radio Access Networks (RANs) are rapidly evolving toward disaggregation, virtualization, and open ecosystems, bringing unprecedented flexibility but also increasing operational complexity. Classical model-driven optimization and rule-based control are increasingly strained by non-stationary propagation, traffic variability, multi-service heterogeneity, and tightly coupled cross-layer interactions across the RAN stack. These trends call for a paradigm shift from “AI as an add-on optimizer” to “AI as a first-class architectural component” of future RANs, where learning, inference, and decision-making are embedded into the RAN architecture while explicitly accounting for real-time constraints, reliability targets, and multi-vendor interoperability.
This workshop focuses on the architectural, algorithmic, and system-level foundations of AI-Native RAN, and on how modern AI, particularly foundation models, GenAI, LLMs, and agentic AI, can enable intent-driven operation, policy generation, knowledge reuse, and distributed coordination among RAN entities. We aim to connect AI-native RAN design with closed-loop learning-and-control, RAN Intelligent Controller (RAN)-enabled intelligence, and practical deployment considerations, and to foster reproducible research through datasets and prototype validations in open/disaggregated RAN settings.
Submission Deadline:
Aug. 31, 2026
Camera Ready:
Sep. 30, 2026
Workshop Date:
Nov. 26, 2026
Topics of Interest Include, but are not Limited to
• AI-native RAN architectures and system design for disaggregated/open and cloud/edge-native RAN
• RIC-enabled intelligence and control frameworks (near-real-time (RT)/non-RT)
•Closed-loop learning-and-control for RAN
•Learning-driven radio resource management
•Foundation models/GenAI/LLM-enabled RAN operation
•LLM/GenAI for telecom knowledge engineering (retrieval-augmented generation (RAG)/knowledge graphs)
•Agentic and multi-agent intelligence for distributed RAN coordination
•Data-centric AI-RAN pipelines (telemetry, labeling/weak supervision, privacy-preserving data sharing, and continual learning)
•Digital twins/simulators/world models for RAN (sim-to-real transfer, synthetic data generation)
•Efficient AI for RAN and AI on RAN (edge deployment, acceleration/compression, task scheduling)
•Trustworthy and secure AI-RAN (attack detection/mitigation, explainability and traceability)
•Testbeds, datasets, over the air validation, and reproducible benchmarking
Steering Committee Members
Prof. Shui Yu, IEEE Fellow, University of Technology Sydney, shui.yu@uts.edu.au, Google Scholar
Prof. Zhu Han, IEEE Fellow, University of Houston, zhan2@uh.edu, Google Scholar
Prof. Linghe Kong, IEEE Fellow, Shanghai Jiao Tong University, linghe.kong@sjtu.edu.cn, Google Scholar
Prof. Jie Xu, IEEE Fellow, The Chinese University of Hong Kong, Shenzhen, xujie@cuhk.edu.cn, Google Scholar
Prof. Celimuge Wu, The University of Electro-Communications, Japan, celimuge@uec.ac.jp, Google Scholar
Prof. Amine EL Moutaouakil, United Arab Emirates University, a.elmoutaouakil@uaeu.ac.ae, Google Scholar
Prof. Hai Liu, The Hang Seng University of Hong Kong, hliu@hsu.edu.hk, Google Scholar
Workshop Co-chairs
Dr. Yulan Gao, KTH Royal Institute of Technology, yulang@kth.se, Google Scholar
Prof. Xiaoming Yuan, Northeastern University, Qinhuangdao, yuanxiaoming@neuq.edu.cn, Google Scholar
Dr. Zhonghao Lyu, KTH Royal Institute of Technology, lzhon@kth.se, Google Scholar
Prof. Xiaowen Cao, Shenzhen University, caoxwen@szu.edu.cn, Google Scholar
Prof. Tan Li, The Hang Seng University of Hong Kong, tanli@hsu.edu.hk, Google Scholar
Prof. Guangxu Zhu, Shenzhen Research Institute of Big Data, gxzhu@sribd.cn, Google Scholar
Dr. Yuchen Li, Baidu Inc. & Shanghai Jiao Tong University, yuchenli@sjtu.edu.cn, Google Scholar
Dr. Shihang Lu, Huawei Inc., ychlushihang@gmail.com, Google Scholar
Submission Notification
https://www.sigmobile.org/mobihoc/2026/submission.html
The page length limit for all initial submissions for review is SIX (6) printed pages (10-point font) and must be written in English. Initial submissions longer than SIX (6) pages will be rejected without review. Papers should be submitted via the submission link.