StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 17 days ago • 445
SkillOpt: Executive Strategy for Self-Evolving Agent Skills Paper • 2605.23904 • Published May 22 • 264
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 357