Preprint · 2026 · Open access
Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems
arXiv (Cornell University) · Published 26 May 2026 · DOI 10.48550/arxiv.2605.27766
In brief
“Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems” is a 2026 preprint by Aman Priyanshu and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 40
- Authors
- 3
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 violations (CIMemories 19.95% to Ours 45.30% across OpenAI models), that leakage is socially contagious, with agents 8 times more likely to disclose sensitive information after observing a peer do so, and that explicit privacy instructions reduce but do not eliminate this effect, leaving leakage rates above 37.8% even with safeguards. Our findings suggest that static chat based safety benchmarks systematically underestimate risks in agentic deployment, and that social context alone is sufficient to elicit sensitive disclosures that single turn evaluations would never surface.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Priyanshu, A., Vijay, S., & Pahwa, E. (2026). Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.27766
MLA 9
Priyanshu, Aman, et al. “Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.27766.
Chicago
Priyanshu, Aman, Supriti Vijay, and Esha Pahwa. 2026. “Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.27766.
Harvard
Priyanshu, A., Vijay, S. and Pahwa, E. (2026) ‘Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems’, arXiv (Cornell University). doi:10.48550/arxiv.2605.27766.
IEEE
A. Priyanshu, S. Vijay, and E. Pahwa, “Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.27766.
BibTeX
@misc{priyanshu2026secret,
title = {{Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems}},
author = {Priyanshu, Aman and Vijay, Supriti and Pahwa, Esha},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2605.27766},
url = {https://doi.org/10.48550/arxiv.2605.27766}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- LLM agents
- privacy
- multi-agent systems
- social pressure
- information leakage
- social contagion
- agent-based modeling
- safety benchmark
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Priyanshu, A., Vijay, S., & Pahwa, E. (2026). Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.27766
How many times has this paper been cited?
0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Aman Priyanshu, Supriti Vijay, Esha Pahwa.
What is the DOI of this paper?
10.48550/arxiv.2605.27766, permanently at https://doi.org/10.48550/arxiv.2605.27766. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.