Preprint · 2026 · Open access

EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents

Fengzhou Sun, Yuan Zhang, Xintong Yu, Jinyao Yan

arXiv (Cornell University) · Published 28 September 2026 · DOI 10.48550/arxiv.2609.35233

Open PDFView at the publisherCite this paper

In brief

“EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents” is a 2026 preprint by Fengzhou Sun and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
0
References
16
Authors
4

Abstract

Large language model (LLM) agents face critical privacy risks when acting as delegates in human-agent-human communication. To prevent such breaches, agents must understand users' social relationships and adhere to context-dependent social information disclosure boundaries. Current studies on agent memory privacy focus on instantaneous interactions, leaving the long-term relational disclosure problem unexplored. In this paper, we propose EP-Mem, an Elastic Privacy Memory architecture that reframes privacy as user-owned boundary control across social roles. EP-Mem introduces (1) token-level memory driven by user-configurable a privacy policy that stratifies persons and events, combining domain-level default circulation rules with fact-level whitelist/blacklist exceptions; and (2) a pluggable sidecar with a privacy engine that aligns disclosure controls with memory across summary, detail, and boundary granularities, enforced throughout generation, storage, and retrieval. We construct EP-Bench, to our knowledge the first long-term multi-party benchmark with cross-session correlated events for policy-conditioned relational disclosure. Experiments show that EP-Mem achieves 94.0% privacy classification accuracy, improves disclosure-permission judgment from 22% to 68%, and reduces privacy leakage by 75.6%, while maintaining retrieval performance and cross-benchmark generalization.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Sun, F., Zhang, Y., Yu, X., & Yan, J. (2026). EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.35233

MLA 9

Sun, Fengzhou, et al. “EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.35233.

Chicago

Sun, Fengzhou, Yuan Zhang, Xintong Yu, and Jinyao Yan. 2026. “EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.35233.

Harvard

Sun, F. et al. (2026) ‘EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2609.35233.

IEEE

F. Sun, Y. Zhang, X. Yu, and J. Yan, “EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.35233.

BibTeX

@misc{sun2026elastic,
  title     = {{EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents}},
  author    = {Sun, Fengzhou and Zhang, Yuan and Yu, Xintong and Yan, Jinyao},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2609.35233},
  url       = {https://doi.org/10.48550/arxiv.2609.35233}
}

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 leakage
  • human-agent communication

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Sun, F., Zhang, Y., Yu, X., & Yan, J. (2026). EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.35233

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?

Fengzhou Sun, Yuan Zhang, Xintong Yu, Jinyao Yan.

What is the DOI of this paper?

10.48550/arxiv.2609.35233, permanently at https://doi.org/10.48550/arxiv.2609.35233. 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.