feat(agent): add GUI-Owl model support#910
Open
Fizza-Mukhtar wants to merge 1 commit intotrycua:mainfrom
Open
Conversation
Contributor
|
@Fizza-Mukhtar is attempting to deploy a commit to the Cua Team on Vercel. A member of the Team first needs to authorize it. |
Contributor
Author
|
@f-trycua @ddupont808 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds first-class agent support for GUI-Owl, a model family from the Mobile-Agent-V3 project, enabling it to be used within the existing CUA agent framework.
The integration follows the same design and conventions as existing agents (e.g. Gemini), ensuring consistency and ease of extension.
What’s included
New GUIOwlAgent implementation (gui_owl.py)
Registration via the agent registry using @register_agent("gui-owl")
Agent discoverable through list_agents() and loadable via get_agent("gui-owl")
No breaking changes to existing agents or configs
Verification / Testing
The following local, non-GPU tests were performed:
from cua_bench.agents import list_agents, get_agent
assert "gui-owl" in list_agents()
assert get_agent("gui-owl") is not None
Output confirms successful registration and loading:
['cua-agent', 'gemini', 'gui-owl']
<class 'cua_bench.agents.gui_owl.GUIOwlAgent'>
Notes on evaluation
Full benchmark runs (e.g. ScreenSpot / OSWorld / Android Control) were not executed locally due to hardware (GPU) limitations.
This PR focuses on infrastructure-level integration, enabling downstream users and CI environments with appropriate hardware to run full evals without additional changes.
Why this matters
GUI-Owl is a strong GUI-automation-focused model family, and this integration makes it immediately usable within the CUA agent ecosystem with minimal friction.
closes #374