省流：我们基于 AutoGLM 和 GELab-Zero 这类 开源 GUI model ，构建了一个 GUI Agent --- OMG-Agent！已开源先是豆包手机证明 AI ...

近日，微软研究团队发布了一篇长达 80 页、逾 3 万字的综述论文《Large Language Model-Brained GUI Agents: A Survey》。这份综述系统梳理了大模型驱动的 GUI 智能体在现状、技术框架、挑战与应用等方面的研究进展。论文指出，通过将大语言模型（LLMs）与多模态模型（Visual Language Models, VLMs）相结合，GUI ...

12月17日，阶跃星辰升级发布了全新的 AI Agent 系列模型「Step-GUI」，包括云端模型 Step-GUI、首个面向 GUI Agent 的 MCP 协议，以及业内首个支持手机部署的开源端侧模型 Step-GUI Edge。

近期，多款应用对努比亚M53（豆包手机）的封禁名单持续扩大，微信、支付宝、拼多多、淘宝等主流电商平台，以及多家银行类应用，均在不同程度上限制了用户在该机型上的登录与使用。这一现象背后，折射出智能体AI与现有互联网生态之间的深层矛盾。 以“帮我比价下单”为例，豆包手机助手通过GUI Agent技术，让AI直接解析手机界面元素，模拟用户操作流程，实现从跳转页面到完成结算的全自动化。这种不依赖官方接口的 ...

A graphical user interface (or GUI, often pronounced "gooey"), is a particular case of user interface for interacting with a computer which employs graphical images and widgets in addition to text to ...

A graphical user interface (GUI, pronounced “gooey”) is a computer environment that simplifies the user’s interaction with the computer by representing programs, commands, files, and other options as ...

A graphical user interface (GUI) allows users to interact with graphics appearing on electronic devices (eg, smartphones, tablets and netbooks). Typically, a user interacts with a GUI by pressing ...

Apple was granted a patent on Tuesday related to a GUI modified for disabled users of iOS devices and MacBooks. Entitled “Devices, Methods & GUI’s for Accessibility using a Touch-Sensitive Surface,” ...

It wasn't just cost and Moore's law. The graphical user interface -- now known as the GUI ("gooey") -- is what really made computing widespread, personal and ubiquitous. Its friendly icons and ...

This is an Insight article, written by a selected contributor as part of WTR's co-published content. Read more on Insight A graphical user interface (GUI) allows users to interact with graphics ...