HARP: Measuring Harm Amplification in Multi-Agent LLM Systems 事件

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems arXiv:2605.27489v1 Announce Type: cross Abstract: Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused by other agents and amplified into system-level harm. We introduce HARP (Harm Amplification through Role Perturbation), a trace-first methodology fo