This paper proposes ToolCUA, an end-to-end agent designed to learn optimal GUI-Tool path selection through a staged training paradigm, and introduces an Interleaved GUI-Tool Trajectory Scaling Pipeline that repurposes abundant static GUI trajectories and synthesizes a grounded tool library, enabling diverse GUI-Tool tr...
Xuhao Hu, Xi Zhang, Hai-Yang Xu et al.· arXiv.org· 9 citations· ⚡4
This work introduces RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover its behavior and build a faithful implementation with no prescribed workflow, and introduces RecreationBench, comprising 250 diverse tasks across domains and platforms.
Shuai Bai, Jia-Yong Deng, Si-Cheng Fan et al.· 1 citation
GMA is presented, a benchmark for evaluating general mobile assistants in challenging real-world scenarios, and shows that appropriate harness design can meaningfully improve performance, particularly on demanding workflows, while the effectiveness of specific designs can vary across foundation models.
Yi-Qi Zhu, Feiyu Gao, Jiakang Fan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.