2025
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ICLR 2025poster
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents---which use external tools and can execute multi-stage tasks---may pose a greater…