StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 6 days ago • 430
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published 17 days ago • 51