Preprint · 2026 · Open access

Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents

Jinming Hu, Haodong Zhao, Qi Jia, Die Chen, Tianhang Zhao, Sufeng Duan, Gongshen Liu

arXiv (Cornell University) · Published 26 September 2026 · DOI 10.48550/arxiv.2609.32511

Open PDFView at the publisherCite this paper

In brief

“Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents” is a 2026 preprint by Jinming Hu and 6 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
22
Authors
7

Abstract

Large language model (LLM) agents serving different users often solve related tasks, yet separate user histories can leave reusable experience inaccessible to other agents. Pooling memories expands access but risks transferring preferences that conflict with the receiving user's requirements. We introduce ShareMem, a memory architecture that shares reusable experience while grounding its application in the receiving user's own preferences. Shared experiences indicate how to act and which preferences to consult; the receiving user's memory supplies their concrete values. Two-stage consolidation refines experience locally before integrating accepted edits into a shared pool. During execution, scope-first retrieval jointly selects local and shared experiences under a common entry budget, while a user-bound channel supports initial and agent-initiated preference retrieval. We evaluate ShareMem across web navigation (Mind2Web), online personalized interaction (VitaBench~2.0), and multi-session coding (MemoryCode) with four backbone models. It improves step success, average task success, and dialogue-macro coding scores, respectively, over matched user-local memory across all four models. Ablations favor two-stage consolidation for smaller shared pools, lower induction token usage, and better downstream performance, and support complementarity between experience guidance and active preference retrieval. Further analyses show that sharing helps most when relevant local experience is scarce, while source quality and cross-user preference interference limit useful transfer.

Cite this paper

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

APA 7

Hu, J., Zhao, H., Jia, Q., Chen, D., Zhao, T., Duan, S., & Liu, G. (2026). Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.32511

MLA 9

Hu, Jinming, et al. “Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.32511.

Chicago

Hu, Jinming, Haodong Zhao, Qi Jia, Die Chen, Tianhang Zhao, Sufeng Duan, and Gongshen Liu. 2026. “Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.32511.

Harvard

Hu, J. et al. (2026) ‘Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2609.32511.

IEEE

J. Hu et al., “Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.32511.

BibTeX

@misc{hu2026learning,
  title     = {{Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents}},
  author    = {Hu, Jinming and Zhao, Haodong and Jia, Qi and Chen, Die and Zhao, Tianhang and Duan, Sufeng and Liu, Gongshen},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2609.32511},
  url       = {https://doi.org/10.48550/arxiv.2609.32511}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning

  • LLM agents
  • user preferences
  • memory consolidation
  • experience transfer
  • web navigation
  • personalized interaction

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?

Hu, J., Zhao, H., Jia, Q., Chen, D., Zhao, T., Duan, S., & Liu, G. (2026). Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.32511

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?

Jinming Hu, Haodong Zhao, Qi Jia, Die Chen, Tianhang Zhao, Sufeng Duan, Gongshen Liu.

What is the DOI of this paper?

10.48550/arxiv.2609.32511, permanently at https://doi.org/10.48550/arxiv.2609.32511. 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.