Long-Horizon Agents Collection Evaluation and training for capable long-horizon agents. • 3 items • Updated 11 days ago
Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning Paper • 2611.12865 • Published 13 days ago • 6
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents Paper • 2609.34518 • Published Sep 28 • 5
Attack & Defense Collection Agentic attacks, intervention, and state-aware safety. • 6 items • Updated Sep 29
Long-Horizon Agents Collection Evaluation and training for capable long-horizon agents. • 3 items • Updated 11 days ago
Physical Privacy Collection Privacy for AI systems embedded in physical and social environments. • 4 items • Updated Sep 30
Attack & Defense Collection Agentic attacks, intervention, and state-aware safety. • 6 items • Updated Sep 29