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

Can the model make assertions about the page? Just like doing ui automation testing, the core is to assert the presence or absence of elements #52

Open Luoxin0903 opened 6 months ago

Luoxin0903 commented 6 months ago

Can the model make assertions about the page? Just like doing ui automation testing, the core is to assert the presence or absence of elements

Youjin1985 commented 2 months ago

I second this question