We are working to apply the ideas of R1 to computer use. The primary struggle is creating reliable neural reward models since hard-verification rewards are not available at scale in GUI interactions.
Our team is currently deep in the weeds of collecting reasoning annotation data for GUI interfaces to train a reliable reward model.
We would love all thoughts, feedback, and collaborations!
We are working to apply the ideas of R1 to computer use. The primary struggle is creating reliable neural reward models since hard-verification rewards are not available at scale in GUI interactions.
Our team is currently deep in the weeds of collecting reasoning annotation data for GUI interfaces to train a reliable reward model.
We would love all thoughts, feedback, and collaborations!