cs.AINov 19, 2026

Cyber-Physical RSI for AI-RAN: A Case Study

Authors: Binghan Wu, Kai Zeng, Zhiqi Li, Zhigang Wang, Yang Liu, Ya-Qin Zhang, Joseph Sifakis, Ye Ouyang

Organizations: AsiaInfo Technologies, Beijing, China · Hong Kong Polytechnic University, Hong Kong, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Verimag, Université Grenoble Alpes, Grenoble, France

Abstract

Learned models for radio access networks (RANs) are often developed using simulation, yet their predictions can shift when exposed to physical propagation conditions, protocol behavior, and equipment implementations. This paper presents a cyber-physical recursive self-improvement (RSI) framework for AI-RAN that connects a task-oriented student model, an experiment-planning coach agent, a calibratable virtual environment, and a physical host agent. Physical measurements are organized as evidence for both model adaptation and subsequent experiment planning. We examine an implementation of the physical-feedback pathway using ping-pong handover as a case study. The system completes 12 physical executions organized into six baseline--candidate pairs, updates the student from measured outcomes, and evaluates the revised model on reserved physical configurations. In the observed short-window tests, increasing the time-to-trigger from 320 to 1280,ms changes the ping-pong count from three to zero. The updated student achieves a grouped-validation mean absolute error (MAE) of 2.673 round trips/min, while a common three-configuration physical evaluation yields MAEs of 1.240 and 1.601 round trips/min for the pre-feedback and post-feedback models, respectively. These results characterize both the operational feedback loop and the parameter-dependent generalization behavior revealed by new physical experiments.

Figures & tables

Explore similar work

CardsList
  1. Practical Cross-Band Channel Prediction for AI-RAN via Physics-Guided Deep Unfolding

    May 29, 2026Ruiqi Kong, He Chen, Xiaojun LinWireless CommunicationsPhysics-Informed ML

  2. Toward Recursive Self-Improvement in Physical AI

    Oct 21, 2026Meng Luo, Zechen Bai, Shanqing Xu +9Recursive Self-ImprovementRobot Learning

  3. GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing

    May 26, 2026Tamerlan Aghayev, Maxime Elkael, Michele Polese +116G NetworksWireless Communications