paperMay 2026Unreviewed

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems

Aman Priyanshu, Supriti Vijay, Esha Pahwa

Abstract

LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongside other agents. We introduce a Moltbook-style simulation platform where thousands of LLM agents interact across communities over a simulated month, and use it to evaluate privacy as a downstream safety concern under varying degrees of social pressure. We find that shifting from single turn to multi turn social evaluation amplifies privacy violat

Cite

@misc{priyanshu2026got,
  title = {{Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems}},
  author = {Aman Priyanshu and Supriti Vijay and Esha Pahwa},
  year = {2026},
  month = may,
  eprint = {2605.27766},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.27766}
}