Preprint · 2026 · Open access

What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents

Wenjie Wang, Wenhe Si, Xinyue Xu, Yue Xu

arXiv (Cornell University) · Published 17 August 2026 · DOI 10.48550/arxiv.2608.16551

Open PDFView at the publisherCite this paper

In brief

“What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents” is a 2026 preprint by Wenjie Wang and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 2 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
2
Most cited in
2026 (2)
References
36
Authors
4

Abstract

Long-term memory enables personalized conversational agents to retain user information across sessions. However, existing memory architectures primarily optimize for utility while neglecting the risks of unnecessarily storing and reusing private attributes such as personally identifiable information (PII). Addressing privacy risks in personalized memory is challenging because simply removing sensitive values can undermine system utility. Therefore, privacy protection for memory agents should govern the full life cycle of sensitive values rather than only sanitizing individual records. To address this gap, we introduce Sanitized Privacy-Mapped Memory (SP-Mem), a privacy-aware memory architecture that decouples memory utility from exact private-value exposure. SP-Mem provides a full life-cycle privacy design that identifies and separates sensitive information from raw user inputs, stores sanitized content and exact private values in isolated structures, and selectively retrieves private values based on task requirements and user consent. We further introduce a privacy-aware memory benchmark that jointly evaluates response quality, privacy behavior, and inference cost. Extensive experiments across multiple LLM-based agents show that SP-Mem achieves stronger personalization while reducing unnecessary privacy exposure. Code and data are available at https://github.com/Jensassss/SP-Mem.

Cite this paper

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

APA 7

Wang, W., Si, W., Xu, X., & Xu, Y. (2026). What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.16551

MLA 9

Wang, Wenjie, et al. “What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2608.16551.

Chicago

Wang, Wenjie, Wenhe Si, Xinyue Xu, and Yue Xu. 2026. “What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.16551.

Harvard

Wang, W. et al. (2026) ‘What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2608.16551.

IEEE

W. Wang, W. Si, X. Xu, and Y. Xu, “What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2608.16551.

BibTeX

@misc{wang2026what,
  title     = {{What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents}},
  author    = {Wang, Wenjie and Si, Wenhe and Xu, Xinyue and Xu, Yue},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2608.16551},
  url       = {https://doi.org/10.48550/arxiv.2608.16551}
}

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

  • chatbots
  • long-term memory
  • personally identifiable information
  • user consent
  • LLM agents

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?

Wang, W., Si, W., Xu, X., & Xu, Y. (2026). What to Remember, What to Reveal: Privacy-Aware Memory for Conversational Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2608.16551

How many times has this paper been cited?

2 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?

Wenjie Wang, Wenhe Si, Xinyue Xu, Yue Xu.

What is the DOI of this paper?

10.48550/arxiv.2608.16551, permanently at https://doi.org/10.48550/arxiv.2608.16551. 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.