GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents Paper • 2606.24551 • Published 6 days ago • 25
Qwen-AgentWorld: Language World Models for General Agents Paper • 2606.24597 • Published 5 days ago • 133
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models Paper • 2606.16140 • Published 13 days ago • 119
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery Paper • 2606.13662 • Published 17 days ago • 28
Benchmarking AI Agents for Addressing Scientific Challenges Across Scales Paper • 2606.12736 • Published 18 days ago • 5
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding Paper • 2606.05259 • Published 25 days ago • 39
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding Paper • 2606.05259 • Published 25 days ago • 39
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research Paper • 2605.26114 • Published May 25 • 65
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents Paper • 2605.25624 • Published May 25 • 34
A Survey of Reasoning-Intensive Retrieval: Progress and Challenges Paper • 2605.00063 • Published Apr 30
OpenComputer: Verifiable Software Worlds for Computer-Use Agents Paper • 2605.19769 • Published May 19 • 85
OpenComputer: Verifiable Software Worlds for Computer-Use Agents Paper • 2605.19769 • Published May 19 • 85