StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 8 days ago • 435
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published 25 days ago • 71
SkillOpt: Executive Strategy for Self-Evolving Agent Skills Paper • 2605.23904 • Published May 22 • 264
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization Paper • 2605.15824 • Published May 15 • 67
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 356
Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback Paper • 2506.11930 • Published Jun 13, 2025 • 53