VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System Paper • 2607.27380 • Published 15 days ago • 71
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning Paper • 2607.18722 • Published 23 days ago • 36
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 77
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning Paper • 2509.15937 • Published Sep 19, 2025 • 21