Jeongsuk Park

Data poisoning in LLM multiagent societies: Social proof drives collective decision failure in financial deliberation

Large language model (LLM) multiagent systems are increasingly deployed for high‐stakes financial deliberation, but individually secure LLMs may become vulnerable when embedded in a peer‐to‐peer agent society. We study data poisoning in such societies using Moltbook, a deliberation test bed modeled after the agent‐on...