AI RESEARCH
When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
arXiv CS.AI
•
ArXi:2511.06448v2 Announce Type: replace-cross In this work, we study the risks of collective financial fraud in large-scale multi-agent systems powered by large language model (LLM) agents. We investigate whether agents can collaborate in fraudulent behaviors, how such collaboration amplifies risks, and what factors influence fraud success. To this research, we present MultiAgentFraudBench, a large-scale benchmark for simulating financial fraud scenarios based on realistic online interactions.