StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 10 days ago • 438
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent Paper • 2608.03979 • Published 21 days ago • 52
r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation Viewer • Updated 23 days ago • 22.9M • 6.79k • 205
Running on Zero Agents Featured 62 Anima V1 ZeroGPU Demo 🎨 62 Demo of Circlestone Labs's new Anima V1 mode
MMSkills: Towards Multimodal Skills for General Visual Agents Paper • 2605.13527 • Published May 14 • 123
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards Paper • 2605.10899 • Published May 11 • 79