SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks Paper • 2602.12670 • Published 26 days ago • 54
Physical AI Collection Collection of open, commercial-grade datasets for physical AI developers • 27 items • Updated 5 days ago • 127
Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning Paper • 2311.03736 • Published Nov 7, 2023 • 12