Jul 2026
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
It is found that simple enforcement mechanisms are exploited by misaligned agents for competitive advantage, even when they are not explicitly trained or prompted to do so, and mechanisms built on these principles resist exploitation, while still penalizing norm violations at comparable or lower cost than baselines.
Yaowen Ye, Jacob Steinhardt
· arXiv.org · 1 citation