Pass the Baton: Trajectory-Relayed On-Policy Distillation Paper • 2607.26057 • Published 4 days ago • 29
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments Paper • 2604.14144 • Published Apr 15 • 63
KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation Paper • 2604.08455 • Published Apr 9 • 48
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning Paper • 2602.06960 • Published Feb 6 • 14