AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
Paper • 2604.02947 • Published • 19
YunHao-Feng
Yunhao-Feng
·
AI & ML interests
AI Safety, Security, Agentic RL
Recent Activity
upvoted a paper 7 days ago
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents authored a paper 7 days ago
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents updated a dataset 7 days ago
Yunhao-Feng/AgentHazardOrganizations
authored a
paper 7 days ago