CUA-frontier Loading Submit a task

Area · 3 projects Priority

Collaboration

Can people, each working through their own computer-use agent, reconcile their changes to one application's code, visuals and running behavior, and keep what each of them needs even when their work is out of sync?

More people now work through an agent of their own, on products whose parts other people own. Two changes can merge cleanly and still break what a user sees; a fix that looks right can quietly undo someone else's feature; and work published late arrives without the reasons behind it. Projects here give each person their own CUA agent on a shared application, where finding and fixing such a conflict takes running the application and looking at it. Games are the first testbed and large 3D design the second.

Projects

Each project is a direction with room for many kinds of task. Its page says what it asks and what a verifier there should establish.

Shared game development

 Start here

Two people develop one game, each through their own computer-use agent. Each person's change passes its own checks, but together they break something that shows in the running game. The agents have to find it by running and watching the game, settle a fix with both people, and keep both features.

Can two units, each a person and their own CUA agent, find and resolve a conflict between their changes to a game's code, scenes and running state by investigating the game itself, without giving up either person's requirements?

0 tasksOpen the project →

Asynchronous integration

 Second stage

Each person works with their own agent for a long stretch before publishing, so the two units build on different versions of a shared application and look at different builds. When the work meets, the published diff lacks the reasons behind it and old captures show a build that no longer exists. The agents have to line up versions, recover the intent, and keep both features.

When units publish late against different versions, can they tell which build and evidence is current, recover why the other unit made its choices, and integrate without silently undoing either person's work?

0 tasksOpen the project →

Shared 3D design

 Second domain

Two people work on one large 3D model, such as a facility with a modular layout, moving assemblies and a review walkthrough, each through their own CUA agent. One changes the layout, the other the motion and the review views. Together they can block a moving assembly or a required view while every file stays valid.

Do the coordination problems the game testbed measures carry over to large 3D design, where a valid layout change can obstruct a moving assembly or a required review view?

0 tasksOpen the project →

Propose a project

Have a question in Collaboration that current benchmarks miss? Propose it as a project: the question, what tasks could look like, and how they could be verified.

opens a GitHub issuePropose →

Tasks in this area

Claims, open pull requests and merged tasks across its projects, from the board.