InternLM / InternLM/Intern-S1

GUI agent capability?

Open
#10 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
No language data
Stars
861
Forks
51
Avg merge
1m
Merged PRs (30d)
1

Description

What about its ability as a GUI agent?
(1) given a GUI task, history actions (including latest history screenshots) and current screenshot, it good at planning next best action to complete the GUI task (e.g., task: booking a flight from Shenzhen to Beijing on August 4 on https://us.trip.com/)?
(2) Can it accurately locate elements (e.g., buttons) on the web UI?
Was related data also included during training?

I think for (1), there must be strong reasoning ability, not sure if model was also trained with this type of data?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.