AI agents have drawn increasing attention mostly on their ability to perceive environments, understand tasks, and autonomously achieve goals. To advance research on AI agents in mobile scenarios, we introduce the Android Multi-annotation EXpo (AMEX), a comprehensive, large-scale dataset designed for generalist mobile GUI-control agents. Their capabilities of completing complex tasks by directly interacting with the graphical user interface (GUI) on mobile devices are trained and evaluated with the proposed dataset. AMEX comprises over 104K high-resolution screenshots from 110 popular mobile applications, which are annotated at multiple levels. Unlike existing mobile device-control datasets, e.g., MoTIF, AitW, etc., AMEX includes three levels of annotations: GUI interactive element grounding, GUI screen and element functionality descriptions, and complex natural language instructions, each averaging 13 steps with stepwise GUI-action chains. We develop this dataset from a more instructive and detailed perspective, complementing the general settings of existing datasets. Additionally, we develop a baseline model SPHINX Agent and compare its performance across state-of-the-art agents trained on other datasets. To facilitate further research, we open-source our dataset, models, and relevant evaluation tools. The project is available at https://yuxiangchai.github.io/AMEX/
In this paper, the pH-sensitive targeting functional material NGR-poly(2-ethyl-2-oxazoline)-cholesteryl methyl carbonate (NGR-PEtOz-CHMC, NPC) modified quercetin (QUE) liposomes (NPC-QUE-L) was constructed. The structure of NPC was confirmed by infrared spectroscopy (IR) and nuclear magnetic resonance hydrogen spectrum (1H-NMR). Pharmacokinetic results showed that the accumulation of QUE in plasma of the NPC-QUE-L group was 1.28 times and 2.43 times that of the QUE Solution and QUE-L groups, respectively. The release amount of NPC-QUE-L in an acidic environment was significantly higher than in physiological pH value. The order of the tumor cell inhibition rate in different pH environments was NPC-QUE-L > PC-QUE-L > QUE-L. In addition, the cellular uptake of NPC-modified liposomes was higher than that of PC-modified and unmodified liposomes, indicating that NPC had good pH-sensitivity and targeting. In the triple-negative breast cancer (TNBC) model, the relative tumor proliferation rate of NPC-QUE-L is about 73%, which is better than that of the QUE solution group. Western blot results show that NPC-QUE-L can effectively reduce the expression of α-smooth actin and transforming growth factor-β1 in tumor tissues, and improve the degree of tumor fibrosis. In this study, NPC could endow QUE liposomes with good stability, pH-sensitivity, and targeting, which provides a reference for improving the solubility and targeting of poorly soluble natural drug components.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)