Research
Research proposes LGWM, a world model that verifies GUI agent transitions in representation space
LGWM predicts the next screen's representation without a decoder and reaches 0.987 AUC on RSWT-BENCH at 17 ms per decision. The authors report it matches strong closed-source VLMs while running far faster than generative GUI world models.
Every outlet that ran it 1 article
Hugging Face PapersResearchLead
Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents