WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution Paper • 2610.18067 • Published 9 days ago • 86
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 23 days ago • 549
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 24 days ago • 368
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published 23 days ago • 135
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction Paper • 2608.26005 • Published Aug 26 • 154