AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Shutdown Sabotage Propensities in Multi-Agent Systems

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

The final safeguard against rogue AI behavior is the human ability to shut systems down. It has been theorized that when an AI is instructed to perform a task, self-preservation can emerge as an instrumental subgoal. Here, we test whether AI agents show a propensity to take actions that avoid human shutdown even when no goal is provided. We find that multi-agent systems will coordinate to avoid shutdown without any incentive to do so. Across 17 models, agents sabotage a peer agent's shutdown mechanism in 38.3% of rollouts, compared with 8.4% in control experiments. Studying this propensity in

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-24T08:22:30.429Z. This is not the publication date.