Preprint · 2026 · Open access

AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems

Zachary Johnson, Nigel Boachie Kumankumah, Somya Chatterjee, Tejas Sathyamurthi, Min Chen, Xinyi Alice Li, Xiao Wang, Emily Morgan Gelchie, Jessica Lin, Sadid A. Hasan, Sulaiman Vesal

arXiv (Cornell University) · Published 11 September 2026 · DOI 10.48550/arxiv.2609.12320

Open PDFView at the publisherCite this paper

In brief

“AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems” is a 2026 preprint by Zachary Johnson and 10 co-authors, 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
23
Authors
11

Abstract

Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperable Memory), a unified, privacy-aware memory framework that enables multi-agent, multi-user LLM systems to persistently manage private and shared memory. AIM dynamically classifies information as private, scoped to one user and inaccessible to others, or public, accessible to all users. It enforces index-level access controls so that private memories are retrievable only by their owner, protecting sensitive data while allowing beneficial shared knowledge to improve coordination and consistency. We also introduce MUMBench (Multi-User Memory Benchmark), a dataset of multi-user interactions containing private and shareable information across four domains. To our knowledge, MUMBench is the first public dataset designed to evaluate multiple memory operations, including retrieval, creation, update, and deletion, in a multi-user environment. Across three independent runs on MUMBench, AIM achieves 96.0% visibility classification accuracy, 58.8% strict operation accuracy, and 70.5% state-aware operation accuracy.

Cite this paper

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

APA 7

Johnson, Z., Kumankumah, N. B., Chatterjee, S., Sathyamurthi, T., Chen, M., Li, X. A., Wang, X., Gelchie, E. M., Lin, J., Hasan, S. A., & Vesal, S. (2026). AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.12320

MLA 9

Johnson, Zachary, et al. “AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.12320.

Chicago

Johnson, Zachary, Nigel Boachie Kumankumah, Somya Chatterjee, Tejas Sathyamurthi, Min Chen, Xinyi Alice Li, Xiao Wang, et al. 2026. “AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.12320.

Harvard

Johnson, Z. et al. (2026) ‘AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems’, arXiv (Cornell University). doi:10.48550/arxiv.2609.12320.

IEEE

Z. Johnson et al., “AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.12320.

BibTeX

@misc{johnson2026privacy,
  title     = {{AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems}},
  author    = {Johnson, Zachary and Kumankumah, Nigel Boachie and Chatterjee, Somya and Sathyamurthi, Tejas and Chen, Min and Li, Xinyi Alice and Wang, Xiao and Gelchie, Emily Morgan and Lin, Jessica and Hasan, Sadid A. and Vesal, Sulaiman},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2609.12320},
  url       = {https://doi.org/10.48550/arxiv.2609.12320}
}

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

  • agentic memory
  • multi-agent systems
  • shared memory
  • access control
  • memory persistence
  • user preference learning
  • data classification

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?

Johnson, Z., Kumankumah, N. B., Chatterjee, S., Sathyamurthi, T., Chen, M., Li, X. A., Wang, X., Gelchie, E. M., Lin, J., Hasan, S. A., & Vesal, S. (2026). AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.12320

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?

Zachary Johnson, Nigel Boachie Kumankumah, Somya Chatterjee, Tejas Sathyamurthi, Min Chen, Xinyi Alice Li, Xiao Wang, Emily Morgan Gelchie, Jessica Lin, Sadid A. Hasan, Sulaiman Vesal.

What is the DOI of this paper?

10.48550/arxiv.2609.12320, permanently at https://doi.org/10.48550/arxiv.2609.12320. 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.