StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents Paper • 2607.22798 • Published 9 days ago • 60
Representation Forcing for Bottleneck-Free Unified Multimodal Models Paper • 2605.31604 • Published May 29 • 63
SkillOrchestra: Learning to Route Agents via Skill Transfer Paper • 2602.19672 • Published Feb 23 • 58