AI RESEARCH
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
arXiv CS.LG
•
ArXi:2602.16346v3 Announce Type: replace-cross LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test single-prompt instructions, leaving a gap in measuring how agents end up helping with harmful or illegal tasks over multiple turns. We