SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks Paper • 2602.12670 • Published 12 days ago • 51
Physical AI Collection Collection of open, commercial-grade datasets for physical AI developers • 30 items • Updated 1 day ago • 124
Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning Paper • 2311.03736 • Published Nov 7, 2023 • 12