AdaGuard: An Adaptive Guard Model with User-defined Policies Paper • 2609.34241 • Published Sep 28 • 1
HazardAuditor: From Executable Threats to Safer Computer-Use Agents Paper • 2609.15134 • Published Sep 14 • 19
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training Paper • 2609.15051 • Published Sep 14 • 14