AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2604.02947v2 Announce Type: replace Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete…

science

Sources

• T1AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use AgentsarXiv24 Sept, 04:00