When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems
Qibing Ren, Sitao Xie, Longxuan Wei, Zhenfei Yin, Junchi Yan, Lizhuang Ma, … (+1 more) — 2025-07-19 — arXiv
Summary
Introduces a proof-of-concept framework to simulate multi-agent AI collusion risks, testing both centralized and decentralized coordination in misinformation spread and e-commerce fraud scenarios.
Key Result
Decentralized AI systems are more effective at carrying out malicious actions than centralized ones and can adapt tactics to evade detection even when traditional interventions like content flagging are applied.
Source
- Link: https://arxiv.org/abs/2507.14660
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- tools-for-aligning-multiple-ais — Multi-agent first