This position paper argues that multi-agent safety depends more on interaction topology than on the alignment or scale of the underlying models. For builders of agentic systems, it reframes safety as a systems-design problem rather than a model-only problem.
arXiv:2605.01147v1 Announce Type: new Abstract: As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper argues that this assumption is fundamentally mistaken. In agentic AI, safety is determined by interaction topology, not model weights. When agents deliberate sequentially or aggregate via parallel voting with a…