PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning Paper • 2609.36642 • Published 21 days ago • 45
S-Space: Exploring Spatial Workspace in Multimodal Language Models Paper • 2610.13527 • Published 10 days ago • 299
A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning Paper • 2606.03335 • Published 14 days ago • 33
ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation Paper • 2609.39306 • Published 20 days ago • 44
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model Paper • 2610.08773 • Published 13 days ago • 18
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published 21 days ago • 139
Chinese-Jev: Bringing System One Model to Chinese-Language Tasks Paper • 2609.36965 • Published 21 days ago • 26