digitalcoach-f1630352·1 events·first seen Aliases: DigitalCoach
Researchers introduce DigitalCoach, a multimodal dataset of 72 expert-novice computer use coaching sessions comprising 22,752 dialogue turns grounded in 28.1 hours of screen and input recordings across five software applications. The dataset is used to evaluate whether state-of-the-art models can teach humans to use software, finding that models favor direct instructions over explanations, error diagnosis, and knowledge checks. Interactive evaluation shows model coaches cause passive instruction-following rather than deeper engagement, and models perform poorly at visual grounding in screen context. The work establishes a benchmark for developing more collaborative and pedagogically effective computer-use coaching agents.