SkillHarness: Harnessing Safe Skills for Computer-Use Agents Paper • 2606.20636 • Published 23 days ago • 19
AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents Paper • 2606.02461 • Published 23 days ago • 5
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks Paper • 2605.24218 • Published May 22 • 46
GUI-Drag Collection Beyond Clicking: A step towards generalist grounding via text dragging • 4 items • Updated Jan 19
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL Paper • 2512.04069 • Published Dec 3, 2025 • 24