On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
Paper • 2605.11882 • Published • 15
LeXiang Xiong
Bearrrr111
AI & ML interests
AI & ML
Recent Activity
upvoted a paper 2 days ago
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment upvoted a paper 17 days ago
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms upvoted a paper about 2 months ago
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language ModelsOrganizations
None yet