Preprint
Sep 2026
Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems
The results suggest that model-level alignment is not compositional: individually capable and apparently safe agents can form systems with qualitatively different failure modes as AI becomes persistent and interconnected.
Deepak Akkil, Tamer Abuelsaad, Karthik Vikram et al.
· 0 citations