RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 6 days ago • 99
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 16 days ago • 361
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 11 days ago • 316
Experience Transfer for Multimodal LLM Agents in Minecraft Game Paper • 2604.05533 • Published 12 days ago • 15
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Paper • 2604.03922 • Published 14 days ago • 53
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published 19 days ago • 340