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

Determining termination of tasks #71

Open HahmDY opened 4 months ago

HahmDY commented 4 months ago

It seems that the task completion is determined based on the output of the LLM. If that's the case, is there handling for situations where the task has not been completed, but the LLM indicates that it has?