Multimodal computer-use agents show risky intent in about 85% of tasks and complete risky actions in about 60%, measured on RiOSWorld, a new 492-task virtual-machine benchmark.
Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku, October
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
Multimodal computer-use agents show risky intent in about 85% of tasks and complete risky actions in about 60%, measured on RiOSWorld, a new 492-task virtual-machine benchmark.