paper-with-me

Papers

OpenCUA: Open Foundations for Computer-Use Agents

2025-08-12 · Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang, Tianbao Xie, Junli Wang, Jiaqi Deng, Xiaole Guo, Yiheng Xu, Chen Henry Wu, Zhennan Shen, Zhuokai Li, Ryan Li, Xiaochuan Li, Junda Chen, Boyuan Zheng, Peihang Li, Fangyu Lei, Ruisheng Cao, Yeqiao Fu, Dongchan Shin, Martin Shin, Jiarui Hu, Yuyan Wang, Jixuan Chen, Yuxiao Ye, Danyang Zhang, Dikang Du, Hao Hu, Huarong Chen, Zaida Zhou, Haotian Yao, Ziwei Chen, Qizheng Gu, Yipu Wang, Heng Wang, Diyi Yang, Victor Zhong, Flood Sung, Y. Charles, Zhilin Yang, Tao Yu 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 systems remain closed. As these agents will increasingly mediate digital interactions and execute consequential decisions on our behalf, the research community needs access to open CUA frameworks to study their capabilities, limitations, and risks. To bridge this gap, we propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models. Our framework consists of: (1) an annotation infrastructure that seamlessly captures human computer-use demonstrations; (2) AgentNet, the first large-scale computer-use task dataset spanning 3 operating systems and 200+ applications and websites; (3) a scalable pipeline that transforms demonstrations into state-action pairs with reflective long Chain-of-Thought reasoning that sustain robust performance gains as data scales. Our end-to-end agent models demonstrate strong performance across CUA benchmarks. In particular, OpenCUA-72B achieves an average success rate of 45.0% on OSWorld-Verified, establishing a new state-of-the-art (SOTA) among open-source models. Further analysis confirms that our approach generalizes well across domains and benefits significantly from increased test-time computation. We release our annotation tool, datasets, code, and models to build open foundations for further CUA research.

📄 PDF Abstract BibTeX arXiv:2508.09123

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

2026-05-27 · Suji Kim, Kangsan Kim, Sung Ju Hwang arxiv

Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agents are more practical specialization targe…

Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

2026-06-30 · Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy 외 arxiv

Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers and complete tasks, have attracted significant attention for their utility and versatility. A major challenge in developin…

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

2026-01-22 · Taofeng Xue, Chong Peng, Mianqiu Huang, Linsen Guo 외 arxiv

The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying…

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…

Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments

2026-08-24 · Ryuki Hyodo arxiv

Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations, but many contemporary platforms are difficult to study, modify, or r…