On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
Paper • 2605.11882 • Published • 16
Chen Xinzhe
Asleeep
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment upvoted a paper 23 days ago
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and MechanismsOrganizations
None yet
upvoted a paper 8 days ago