发表机构
National Sun Yat-sen University; National Taiwan University; Chalmers University of Technology（国立中山大学; 国立台湾大学; 查尔姆斯理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出智能体无线数字孪生（AWDT）框架，利用真实世界测量数据自主构建和校准WDT，通过三个智能体迭代优化，将RSRP预测MAE从11.46 dB降至5.25 dB，并展示了跨设备可迁移性。
AI 中文摘要
无线数字孪生（WDT）是开发和评估AI原生无线接入网络的有前景的使能技术，然而构建高保真WDT通常需要大量人工努力来整合异构信息并推断未知的传播相关参数。本文提出智能体WDT（AWDT），一种端到端的智能体框架，利用易于获取的环境信息和从商用智能手机可轻松获得的测量数据，自主构建和校准WDT。AWDT包含三个智能体：EnvAgent构建传播环境，OpAgent推断基站和扇区配置，MatAgent校准无线电材料属性。这些智能体利用LTE/NR参考信号接收功率（RSRP）测量与射线追踪预测之间的差异，迭代优化WDT。真实世界实验表明，AWDT将RSRP预测平均绝对误差（MAE）从11.46 dB降低至5.25 dB，展示了射线追踪保真度的显著提升。使用独立测量系统的评估进一步证明了跨设备可迁移性，且仅需轻量级的设备特定偏差自适应，凸显了智能体AI在有限先验知识下实现可扩展WDT构建与校准的潜力。
英文摘要
Wireless digital twins (WDTs) are promising enablers for developing and evaluating AI-native radio access networks, yet constructing a high-fidelity WDT typically requires substantial manual effort to integrate heterogeneous information and infer unknown propagation-related parameters. This paper proposes Agentic WDT (AWDT), an end-to-end agentic framework for autonomous WDT construction and calibration using readily available environmental information and measurements readily obtainable from commercial smartphones. AWDT comprises three agents: EnvAgent constructs the propagation environment, OpAgent infers BS and sector configurations, and MatAgent calibrates radio material properties. The agents iteratively refine the WDT using discrepancies between LTE/NR reference signal received power (RSRP) measurements and ray-tracing predictions. Real-world experiments show that AWDT reduces the RSRP prediction MAE from 11.46 to 5.25 dB, demonstrating a substantial improvement in ray-tracing fidelity. Evaluation with an independent measurement system further demonstrates cross-device transferability with lightweight device-specific bias adaptation, highlighting the potential of agentic AI for scalable WDT construction and calibration with limited prior knowledge.
Comments6 pages, 6 figures, 1 table. Submitted to IEEE conference
