search

mnotgod96 / AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
https://appagent-official.github.io/
MIT License
4.84k stars 511 forks source link

无法使用human demonstration模式 #48

Closed peng2219 closed 6 months ago

peng2219 commented 6 months ago

使用human demonstration模式，输入了 target app 和goal，显示手机截图，并且有以下提示 “All interactive elements on the screen are labeled with red and blue numeric tags. Elements labeled with red tags are clickable elements; elements labeled with blue tags are scrollable elements.” 之后，一直停在这里，不往下进行，请问如何处理？

mnotgod96 commented 6 months ago

跳出截图窗口后点击键盘上任意一个键就可以在命令行继续输入了

peng2219 commented 6 months ago

感谢， 也是有时 work，有时不 work