Artificial Intelligence #benchmark#atomic skills
ATOM-Bench: New Benchmark Evaluates Atomic Skills and Compositional Generalization in Robotic Manipulation Policies
Researchers introduce ATOM-Bench, a real-world benchmark that factorizes tabletop manipulation into atomic skills and compositional tasks. It includes 30 atomic tasks and 24 held-out compositional tasks across single-arm and dual-arm tracks, with 3,000 human demonstrations. Through 2,700 physical rollouts, the team found that current policies struggle with fine-grained motor skills, counting, and logical filtering, and strong atomic performance does not guarantee compositional transfer.
Jun 16, 2026 1 source