Skip to content

Fix the task ClockStopWatchRunning#358

Open
Jeffjeno wants to merge 2 commits intogoogle-research:mainfrom
Jeffjeno:main
Open

Fix the task ClockStopWatchRunning#358
Jeffjeno wants to merge 2 commits intogoogle-research:mainfrom
Jeffjeno:main

Conversation

@Jeffjeno
Copy link

@Jeffjeno Jeffjeno commented Feb 5, 2026

In our internal evaluations, we found that after the environment has run many tasks, even though clock-related tasks include reset scripts at the start and end (which reset the Clock app), the information shown in the At a Glance module does not get reset. This can cause evaluation errors, where the model mistakenly believes a timer has already started running. Therefore, we added an additional reset step for the At a Glance component.

The screenshots are presened as follows:
Now we start a stopwatch
50aa143d-4068-4690-977e-d07686c941bd

Now we clear and close the app clock,but at the glance module is still running
f75bd406-36ff-41ee-8fe4-f8d1859fa1b4

after we clear the 'as' module , it works
f9c27097-542c-48e7-8344-629f19fff115

@google-cla
Copy link

google-cla bot commented Feb 5, 2026

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

@Jeffjeno Jeffjeno marked this pull request as draft February 5, 2026 15:43
@Jeffjeno Jeffjeno marked this pull request as ready for review February 5, 2026 15:45
@crawles
Copy link
Collaborator

crawles commented Feb 8, 2026

Thanks for the PR! Would you mind signing the contributor license agreement? https://github.com/google-research/android_world/pull/358/checks?check_run_id=62638021569 Then I can submit it

Even if the clock app has been closed and cleared, in andriod emulator we found the stopwatch is still running in the "at a glance box", so we should reset the at the glance module
@Jeffjeno
Copy link
Author

Jeffjeno commented Feb 9, 2026

Thanks for the PR! Would you mind signing the contributor license agreement? https://github.com/google-research/android_world/pull/358/checks?check_run_id=62638021569 Then I can submit it

ok, I've dealed with it!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants