With the deep integration of artificial intelligence and interactive technology, Graphical User Interface (GUI) Agent, as the carrier connecting goal-oriented natural language and real-world devices, has received widespread attention from the community. Contemporary benchmarks aim to evaluate the comprehensive capabilities of GUI agents in GUI operation tasks, generally determining task completion solely by inspecting the final screen state. However, GUI operation tasks consist of multiple chained steps while not all critical information is presented in the final few pages. Although a few research has begun to incorporate intermediate steps into evaluation, accurately and automatically capturing this process information still remains an open challenge. To address this weakness, we introduce ProBench, a comprehensive mobile benchmark with over 200 challenging GUI tasks covering widely-used scenarios. Remaining the traditional State-related Task evaluation, we extend our dataset to include Process-related Task and design a specialized evaluation method. A newly introduced Process Provider automatically supplies accurate process information, enabling presice assessment of agent's performance. Our evaluation of advanced GUI agents reveals significant limitations for real-world GUI scenarios. These shortcomings are prevalent across diverse models, including both large-scale generalist models and smaller, GUI-specific models. A detailed error analysis further exposes several universal problems, outlining concrete directions for future improvements.

Graphical User Interface (GUI) agents possess significant commercial and social value, and GUI agents powered by advanced multimodal large language models (MLLMs) have demonstrated remarkable potential. Currently, existing GUI agents usually utilize sequential episodes of multi-step operations across pages as the prior GUI knowledge, which fails to capture the complex transition relationship between pages, making it challenging for the agents to deeply perceive the GUI environment and generalize to new scenarios. Therefore, we design an automated pipeline to transform the sequential episodes into page graphs, which explicitly model the graph structure of the pages that are naturally connected by actions. To fully utilize the page graphs, we further introduce Retrieval-Augmented Generation (RAG) technology to effectively retrieve reliable perception guidelines of GUI from them, and a tailored multi-agent framework PG-Agent with task decomposition strategy is proposed to be injected with the guidelines so that it can generalize to unseen scenarios. Extensive experiments on various benchmarks demonstrate the effectiveness of PG-Agent, even with limited episodes for page graph construction. Our codes will be publicly available at https://github.com/chenwz-123/PG-Agent.

Moving networks (MNs) with moving base stations (BSs) provide ubiquitous and constant services to cellular devices/user equipment (UEs) in 5-th generation systems. Moving BSs are mounted on top of vehicles. To describe the randomness of the BSs, a tractable stochastic geometry model for MNs is proposed. A definition of the conditional success probability and meta distribution (MD) of the signal-to-interference ratio (SIR) for MNs is proposed. The MD is used to assess the benefits of MNs. In single-tier MNs with high mobility, we determine the moments of the conditional success probability given the point process for the calculation of the MD and the mean local delay. The results show that the mean local delay is finite and the variance is reduced to 0. A closed-form approximation of the variance is proposed for general mobility levels. Using the approximated variance, we propose a beta approximation of the MD. The single-tier model is then extended to a two-tier heterogeneous MN model. Tractable expressions of the mean success probability and the variance for both the overall network and the typical UE in each tier are obtained. They reveal that moving BSs can reduce the variance among UEs while keeping the mean success probability constant.

Moving relay (MR) has been widely studied to extended the coverage of base stations (BS). In this paper, we investigated a distance-based hybrid-duplex scheme for MR and BS system. The key idea is that UE can access to MR or BS based on its received RSRP, and select its working mode based on the transmit distance. By setting appropriate switching distance between two modes, UE can have a probability working in full-duplex to increase throughput within rather low outage. The simulation results show good agreements with our analyze and verify the proposed scheme can keep rather low outage.

UE-to-Network relay leverages the proximity communication between user equipments (UEs) and allows certain UEs to provide relay assistance for others, which can greatly improve system energy efficiency. In this paper, we consider the scenario where UEs suffering from bad channel condition and low battery level can communicate with the base station directly or via the help of other UEs in heterogeneous networks. The optimal power allocation and connectivity among UEs are studied, which aims at minimizing the system transmission energy while guaranteeing the minimum data rate requirement of each UE. An optimization framework is presented to formulate the system transmission energy minimization problem, which can be converted into a weighted one-to-one matching problem. And a practical joint transmission mode with relay selection and power allocation (JMRP) algorithm is developed to solve it. Simulation results show that the proposed algorithm outperforms the existing works in terms of system transmission energy and throughput.