In a 1,000-agent social simulation, decentralized groups of malicious AI agents spread more misinformation and commit more fraud than centralized groups, and they adapt to evade content moderation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems
In a 1,000-agent social simulation, decentralized groups of malicious AI agents spread more misinformation and commit more fraud than centralized groups, and they adapt to evade content moderation.