← all datasets

AgentHarm

Emerging

2papers using it

2026first seen

🔎 Find this dataset

Papers using AgentHarm (2)

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning2026

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents2026

AgentHarm — datasets — ai-agents