Informations fournies par OpenAlex. Research Africa ne déduit ni nationalité, ni poste, ni coordonnées personnelles.
Shuai Bai, Jiayong Deng, Sicheng Fan, Yikun Fu et autres
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore …
Dunjie Lu, Shuai Bai, Tianyi Bai, Sicheng Fan et autres
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B …
Dunjie Lu, Shuai Bai, Tianyi Bai, Sicheng Fan et autres
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B …
Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, Weiming Wu et autres
Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, …
Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, Weiming Wu et autres
Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, …
Bowen Wang, Dunjie Lu, Junli Wang, Tianyi Bai et autres
Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for …
Bowen Wang, Dunjie Lu, Junli Wang, Tianyi Bai et autres
Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for …
cn (code pays fourni par la source)
Dunjie Lu, Yiheng Xu, Haoyuan Wu, Xinyuan Wang et autres
Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgentTrek, a scalable pipeline that automatically mines training data from publicly available screen-recorded videos at web scale, eliminating the need …
Xinyuan Wang, Bowen Wang, Dunjie Lu, Junlin Yang et autres
hk, cn, us, ca (code pays fourni par la source)
Yiheng Xu, Dunjie Lu, Zhi-Qiang Shen, Junli Wang et autres
Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human annotation, making them unsustainable at scale. We propose AgentTrek, a …
Yiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu et autres
Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a unified vision-based framework for autonomous GUI agents that directly operates on screen images, standardizes cross-platform interactions and incorporates structured reasoning …
BNTIC News n’est pas le producteur de ces données. Les publications sont interrogées à la demande dans Crossref, OpenAIRE, DOAJ, Europe PMC, HAL, DataCite, AfricArXiv, ROR et la Banque mondiale, sans clé d’accès. OpenAlex reste optionnel. Aucun service payant n’est nécessaire et aucune donnée externe n’est enregistrée en base. Consulter les sources et leurs limites.
L'essentiel de l'actu tech du Burkina & d'Afrique, chaque semaine dans votre boîte mail.
Gratuit · sans spam · désinscription en un clic