Preprint · 2026 · Open access
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
arXiv (Cornell University) · Published 25 June 2026 · DOI 10.48550/arxiv.2606.26627
In brief
“Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents” is a 2026 preprint by Nada Lahjouji and Ashwin Gerard Colaco, published in arXiv (Cornell University). OpenAlex counts 3 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
- 3
- Most cited in
- 2026 (3)
- References
- 122
- Authors
- 2
Abstract
Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes harder to enforce. An agent touches many data sources, runs multi-step workflows, keeps state across sessions, and acts with delegated permissions. Sensitive information can therefore leak not only through its final answer but through the queries it issues, the intermediate results it handles, the memory it writes, and the messages it exchanges with other agents. We survey the privacy of LLM agents from a data-centric view, organizing the field around the data an agent touches rather than by attack type, and we use data agent as shorthand for an LLM agent that works with data. Research on these risks is active but scattered across retrieval-augmented generation, text-to-SQL interfaces, agent memory, prompt injection, access control, and contextual privacy. This survey brings that work together: we taxonomize the data sources an agent touches, the privacy risks each source creates, and the governance mechanisms that address them; we map the benchmarks used to measure these risks and identify what is missing; and we set out the open problems. Two findings recur: among governance mechanisms only information-flow control covers both compositional and cross-session inference leakage, the two least-protected risks; and no benchmark drives an agent across its data surfaces under one privacy policy, the instrument the field most lacks. Our goal is a reference that situates the scattered literature and gives future work a common framing.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lahjouji, N., & Colaco, A. G. (2026). Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26627
MLA 9
Lahjouji, Nada, and Ashwin Gerard Colaco. “Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.26627.
Chicago
Lahjouji, Nada and Ashwin Gerard Colaco. 2026. “Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26627.
Harvard
Lahjouji, N. and Colaco, A. G. (2026) ‘Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2606.26627.
IEEE
N. Lahjouji and A. G. Colaco, “Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.26627.
BibTeX
@misc{lahjouji2026agents,
title = {{Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents}},
author = {Lahjouji, Nada and Colaco, Ashwin Gerard},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2606.26627},
url = {https://doi.org/10.48550/arxiv.2606.26627}
}
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
- sensitive data leakage
- information flow control
- agent memory
- retrieval-augmented generation
- text-to-SQL
- prompt injection
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?
Lahjouji, N., & Colaco, A. G. (2026). Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26627
How many times has this paper been cited?
3 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?
Nada Lahjouji, Ashwin Gerard Colaco.
What is the DOI of this paper?
10.48550/arxiv.2606.26627, permanently at https://doi.org/10.48550/arxiv.2606.26627. 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.