OSWorld

The 'OSWorld' dataset/benchmark contains data for evaluating the performance of automated agents in interacting with graphical user interfaces (GUIs).

Papers using OSWorld (5)

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent2026Infantagent-next: A Multimodal Generalist Agent For Automated Computer Interaction2025Kimi-VL Technical Report2025 · 1 citesMano Technical Report2025DPO Learning With Llms-judge Signal For Computer Use Agents2025