Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published 7 days ago • 190
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City Paper • 2608.27456 • Published 6 days ago • 109
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs Paper • 2608.20492 • Published 13 days ago • 111
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces Paper • 2608.23041 • Published 9 days ago • 64
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback Paper • 2608.24794 • Published 8 days ago • 6