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 • 428
Running on Zero MCP 1.29k Wan2.2 14B Fast Preview 🐌 1.29k generate a video from an image with a text prompt
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published Jul 16 • 144