StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published Aug 15 • 447
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published Aug 4 • 54
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks Paper • 2510.15019 • Published Oct 16, 2025 • 61