ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
HKUST · East China Normal University · University of Science and Technology of China · Shanghai Jiao Tong University · Shanghai Jiaotong University · The University of Hong Kong · Shanghai Artificial Intelligence Laboratory · Fudan University · Shanghai AI Laboratory · Harbin Institute of Technology · Hong Kong University of Science and Technology · The Chinese University of Hong Kong · Shanghai Artificial Intelligence Laboratory Tsinghua University · Shanghai Aritifcal Intelligence Laboratory
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this work, we introduce ScaleCUA, a step toward scaling open-source CUAs. It offers a large-scale dataset spanning 6 operating systems and 3 task domains, built via a closed-loop pipeline uniting automated agents with human experts. Trained on this scaled-up data, ScaleCUA can operate seamlessly across platforms. Specifically, it delivers strong gains over baselines (+26.6 on WebArena-Lite-v2, +10.7 on ScreenSpot-Pro) and sets new state-of-the-art results (94.4% on MMBench-GUI L1-Hard, 60.6% on OSWorld-G, 47.4% on WebArena-Lite-v2). These findings underscore the power of data-driven scaling for general-purpose computer use agents. We will release data, models, and code to advance future research.