thu-coai/Agent-SafetyBench download history

thu-coai/Agent-SafetyBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 387 times (130 in the last 7 days), and 2,499 times in total. It ranks #40,356 among datasets by monthly downloads.

Agent-SafetyBench is a comprehensive agent safety evaluation benchmark that introduces a diverse array of novel environments that are previously unexplored, and offers broader and more systematic coverage of various risk categories and failure modes. Please visit our Github or check our paper for mo

Open thu-coai/Agent-SafetyBench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.