SOURCE-LINKED INTELLIGENCE

Indirect tipping: a social attack surface in AI agent populations

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on collective equilibria that determine how agent populations process information, prioritize actions, and respond to uncertainty. Yet the same equilibria that enable agents to coordinate also create a social attack surface. The standard framework to assess this vulnerability is critical mass dynamics: the minimum fraction of adversarial agents required to overturn an equilibrium through direct competition. Here, we show that this approach risks underestimati

Read original source ↗ Open in workspace

recordType

paper

region

Global