AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
Paper • 2604.02947 • Published • 15
YunHao-Feng
Yunhao-Feng
·
AI & ML interests
AI Safety, Security, Agentic RL
Recent Activity
upvoted a paper about 9 hours ago
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents authored a paper about 10 hours ago
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents updated a dataset about 15 hours ago
Yunhao-Feng/AgentHazardOrganizations
upvoted a paper about 9 hours ago
authored a
paper about 10 hours ago
updated a
dataset about 15 hours ago
published a
dataset about 15 hours ago