Computer-Using Agent (CUA)
计算机使用代理（Computer-Using Agent, CUA），基于大型多模态模型构建的自主 AI 代理，能像人一样直接操作图形界面（点击按钮、打开窗口、执行界面级动作），代替用户完成电脑操作任务。
English Definition
"An autonomous AI agent, typically built on large multimodal models, that directly manipulates graphical user interfaces (e.g., opening windows, clicking buttons, executing interface-level actions) to perform tasks on behalf of users, operating computers in a human-like manner."
用法说明 · 针对中文母语者
CUA 是 2024-2025 年随着多模态大模型兴起而出现的新概念，强调 AI 不只是回答问题，而是能'使用'电脑。OpenAI 的 Operator（2025 年 1 月发布）是首个被广泛引用的 CUA 实现。
真实用例 · 3 条
"The recent advent of Computer-Using Agents (CUA) based on Large Multimodal Models, which can directly manipulate graphical user interfaces, offers new opportunities for such accessibility."
"Recent advances in Large Multimodal Model (LMM) have led to the emergence of Computer-Using Agent (CUA), which can operate computers like human users (e.g., opening windows, clicking buttons, and executing interface-level actions)."
"We employed Operator, a CUA model released by OpenAI [75] in January 2025, and implemented a Text-to-Speech (TTS) module to automatically detect and vocalize the model's responses."