AdaGuard: An Adaptive Guard Model with User-defined Policies Paper • 2609.34241 • Published 19 days ago • 1
HazardAuditor: From Executable Threats to Safer Computer-Use Agents Paper • 2609.15134 • Published Sep 14 • 19
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification Paper • 2607.01793 • Published Jul 4 • 6