AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published Sep 29 • 87
MassAlloc Attention: Let Attention Allocate Its Own Compute Paper • 2609.32712 • Published Sep 26 • 22
CoWindow Attention: Full Causal Coverage Is a Collective Property Paper • 2609.32704 • Published Sep 26 • 14
MotionVLA: Vision-Language-Action Model for Humanoid Motion Paper • 2606.15142 • Published Jun 13 • 5
MassAlloc Attention: Let Attention Allocate Its Own Compute Paper • 2609.32712 • Published Sep 26 • 22
CoWindow Attention: Full Causal Coverage Is a Collective Property Paper • 2609.32704 • Published Sep 26 • 14
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published Sep 21 • 164