With the rapid growth of IoT and AIoT applications, the demand for customized hardware is surging, yet PCB design for IoT devices remains a heavily manual, GUI-centric process that requires significant expertise in circuit and tools. This creates a widening gap between the accelerated software development and the difficulty of realizing corresponding hardware, making PCB-based hardware a critical bottleneck for system innovation. We present IoTGen, an LLM-driven agentic system that generates IoT PCB designs directly from natural-language demands. IoTGen introduces semantic-rich programming abstractions that capture schematic construction, enabling a domain-specialized language model to synthesize schematics with code. It further integrates a semantic component retrieval algorithm that combines LLM understanding with vector-based search, and an LLM-guided hybrid layout procedure that coordinates auto-routing tools to produce PCB layouts suitable for fabrication. We evaluate IoTGen on a dataset of diverse IoT designs, achieving a high component matching accuracy of 90%, a schematic generation success rate of 82%, and significant layout improvement. Case studies further demonstrate its capability to generate IoT PCB designs while substantially reducing the human effort and domain expertise required for hardware development. We release IoTGen to facilitate further research.

As a key feature that has the potential to enable many advanced applications, the integration of sensing functionality is considered essential in the 6G network, which motivates the design of integrated sensing and communication (ISAC) systems. However, traditional ISAC systems based on non-overlapped resource allocation face the challenge of poor energy and spectral efficiency. In this paper, we implement an ISAC system named Horus based on reconfigurable intelligent surfaces, which provides an energy-efficient solution to sense objects in a wide range of blind areas. With a carefully designed ISAC protocol, Horus can transmit sensing information to the receiver with high spectral efficiency. We have verified the ability of the proposed system in two case studies of multi-modal sensing and around-corner radar early warning, respectively. Our demonstration video can be found in [11].

With the 5G systems being highly developed, the urge of the next generation networks is increasingly necessary, which demands extremely high data rates and low latency. As an emerging technology capable of reflecting and refracting the incident signals on both sides simultaneously, recently the intelligent omnidirectional surface (IOS) has been used to enhance the capacity of wireless networks. However, it is challenging to design an IOS-enabled beamforming scheme that can respond quickly in a varying mobile environment due to its high complexity. In this paper, we aim to maximize the sum rate in an IOS-aided multi-user system given dynamically changing channel states and user mobility. A novel meta-critic reinforcement learning framework named meta-critic deep deterministic policy gradient algorithm is proposed to design the IOS-enabled beamforming scheme. We propose a meta-critic network that can recognize the environment change and automatically perform the self-renewal of the learning model. A stochastic explore-and-reload procedure is also tailored to reduce the high-dimensional action space problem. Simulation results demonstrate that our proposed method outperforms other benchmarks including the state-of-the-art reinforcement learning method in both achievable sum rate and convergence speed.

Received signal strength (RSS) fingerprint map is one of the most widely-used indoor localization approaches, but it often relies on multiple access points (AP) for data collection and suffers from frequent data updates due to dynamic wireless environments. In this work, we implement a reconfigurable-intelligent-surface (RIS) assisted indoor localization system named Meta2Locate to tackle the above issues using only one AP. In the proposed system, we deploy our self-designed RIS at 5.5GHz in an indoor environment, which can customize the propagation channels between the AP and the target. For the changing propagation environment, we design a mean maximum discrepancy weighted meta-learning approach to train a model that maps the RSS fingerprint to the location of the user, and it only needs a few data for the model update.

Capable of reflecting and refracting the incident signals on both sides simultaneously, the intelligent omnidirectional surface (IOS) has recently been proposed as a promising solution to enhance the capacity of wireless networks. However, the large number of IOS elements brings a heavy burden to the beamforming scheme design, especially for applications that require a fast response to varying environments. In this paper, aiming to maximize the sum rate of an IOS-aided multi-user system via IOS-enabled beamforming design that can rapidly adapt to dynamic channel states and user mobility, we develop a novel meta-critic reinforcement learning framework where a meta-critic network recognizes the environment change and automatically re-trains of the learning model. A stochastic Explore and Reload procedure is tailored to reduce the high-dimensional action space problem. Simulation results show the proposed scheme can converge to a higher sum rate more rapidly compared to the benchmark methods in dynamic settings. The robustness of our scheme against different IOS sizes is also verified.