Search papers, labs, and topics across Lattice.
This paper introduces HyMobileAgent, a mobile GUI agent leveraging the Hy3.0-VL-A3B vision-native foundation model to enhance interaction with complex digital environments. By integrating a comprehensive scaling framework that combines data acquisition, mock-interface synthesis, and a structured Planning-and-Reflection mechanism, the authors address critical challenges in mobile agent performance, such as perception accuracy and long-horizon decision-making. The key result is a robust agent capable of efficiently navigating and interacting with a diverse set of applications, significantly improving the quality of data-driven interactions in mobile environments.
Mobile agents can now navigate complex GUIs with unprecedented efficiency, thanks to a novel data-environment co-scaling framework.
As large multimodal models move from understanding content to operating on digital environments, mobile GUI has emerged as a challenging and consequential testbed for digital embodied intelligence. Mobile agents operate under three coupled constraints: precise perception of complex interfaces, scalable acquisition of high-quality interaction data, and robust long-horizon decision making under compounding execution errors. This report presents HyMobileAgent, a mobile GUI agent built on Hy3.0-VL-A3B, a vision-native foundation model featuring native any-resolution input, an A3B-scale deployment budget, and a 32K context window to model extended interaction histories. Rather than relying solely on model scaling, we develop a joint data and environment centric scaling framework to address the key bottlenecks of mobile interaction. Our framework integrates a GUI perception flywheel combining mock-interface synthesis, rejection sampling, and icon-specific augmentation; a knowledge pipeline that transforms tutorial videos into structured interaction data; a million-scale action data pipeline deployed across more than 2000 sandbox and real-device instances with automated failure attribution; the PhoneWorld Mock App Factory, providing a resettable training environment with 34 mock applications and over 34000 tasks; and a structured Planning-and-Reflection mechanism with explicit dead-loop detection for reliable long-horizon execution. We also introduce a progressive training recipe consisting of mid-training, supervised fine-tuning, and reinforcement learning with task-specific reward designs.
