StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 12 days ago • 442
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents Paper • 2607.23588 • Published Jul 26 • 125