Computer-use agents increasingly tackle tasks ranging from everyday desktop activities to long-horizon professional workflows. Yet interfaces centered on screenshots and mouse-and-keyboard actions can impose a human-interaction prior, requiring repeated screen interpretation while leaving the computer's semantic and pr...
Hao-Qing Wang, Xiao-Yi Zhang, Si-Cheng Fan et al.· 0 citations
Multi-Dimensional Conjunctive Preference Optimization (M-DPO) is developed, which enforces simultaneous correctness across all axes and adaptively routes gradients to the most deficient dimension in post-training, bringing open scientific diagram generation close to proprietary-level structural fidelity.
This work formalizes skill optimization via Zeroth-Order (ZO) optimization, mapping classical counterparts (central difference, trust regions) to recent literature to establish three principles for convergence and generalization: file-system-based trajectory exploration, consensus attribute mining, and independent vali...
Yifei Shen, Bo Li, Xinjie Zhang· arXiv.org· 10 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.