MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research Paper • 2605.26114 • Published 10 days ago • 62
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks Paper • 2605.22535 • Published 14 days ago • 9
Synthetic Computers at Scale for Long-Horizon Productivity Simulation Paper • 2604.28181 • Published Apr 30 • 20
δ-mem: Efficient Online Memory for Large Language Models Paper • 2605.12357 • Published 23 days ago • 125
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents Paper • 2604.18543 • Published Apr 20 • 30