paper-with-me

Papers

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

2025-09-18 · Zhaoyang Liu, Jingjing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Xuan Dong, Yue Yu, Chenyu Lu, YunXiang Mo, Yao Yan, Zeyue Tian, Xiao Zhang, Yuan Huang, Yiqian Liu, Weijie Su, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang arxiv

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: https://github.com/OpenGVLab/ScaleCUA.

📄 PDF Abstract BibTeX arXiv:2509.15221

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

2026-03-25 · Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin, Aarash Feizi 외 arxiv

Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, high-quality human demonstration videos. R…

OpenCUA: Open Foundations for Computer-Use Agents

2025-08-12 · Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang 외 arxiv

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA s…

Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs

2026-07-30 · Woongkyu Lee, Jungwook Choi arxiv

Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challengi…

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

2025-11-14 · MiroMind Team, Song Bai, Lidong Bing, Carson Chen 외 arxiv

We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or context length, MiroTh…

Reinforcement Learning

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents

2025-08-19 · Hanyu Lai, Xiao Liu, Yanxiao Zhao, Han Xu 외 arxiv

We introduce ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. ComputerRL features the API-GUI paradigm, which unifies programmatic API call…

Reinforcement Learning