Preprint · 2026 · Open access
Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
arXiv (Cornell University) · Published 13 October 2026 · DOI 10.48550/arxiv.2610.18052
In brief
“Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents” is a 2026 preprint by Bofan Xie and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 1
- Most cited in
- 2026 (1)
- References
- 27
- Authors
- 7
Abstract
Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users increasingly ask them to delete sensitive or outdated facts. A memory system should honor such requests. It should remove exactly what was requested and keep the rest of its memory intact. However, existing memory benchmarks evaluate only memory writing, retrieval, and organization, so whether agents can forget at the user's explicit request remains under-evaluated. To address this gap, we propose Bemula, the first benchmark dedicated to memory unlearning. It comprises 50 multi-session dialogue instances, 135 forget requests of six types, and 1,742 test questions. Each dialogue has a control version without the requests, so that only systems that have stored the target can earn credit for forgetting. Across the paired versions, five test suites measure storage, removal of the requested information, preservation of unrelated memories, relearning of similar facts, and resistance to extraction attacks. On Bemula, we evaluate six mainstream memory systems under three backbone LLMs, together with the Full Context LLM on two of them. The results are negative. Across all evaluated systems and backbones, no system passes more than 1.5% of forget requests end to end, and most pass none at all. These systems either leave the requested information extractable under simple attacks or delete far more than requested. Memory unlearning therefore remains an open challenge for agent memory design. We release our data and code at https://github.com/Nboxff/bemula-benchmark.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Xie, B., Wang, C., Ge, G., Wang, S., Niu, F., Zhang, H., & Wang, W. (2026). Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.18052
MLA 9
Xie, Bofan, et al. “Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.18052.
Chicago
Xie, Bofan, Chaokun Wang, Guanchen Ge, Songyao Wang, Fang Niu, Hang Zhang, and Wei Wang. 2026. “Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.18052.
Harvard
Xie, B. et al. (2026) ‘Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2610.18052.
IEEE
B. Xie et al., “Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.18052.
BibTeX
@misc{xie2026agents,
title = {{Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents}},
author = {Xie, Bofan and Wang, Chaokun and Ge, Guanchen and Wang, Songyao and Niu, Fang and Zhang, Hang and Wang, Wei},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2610.18052},
url = {https://doi.org/10.48550/arxiv.2610.18052}
}
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
- long-term memory
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?
Xie, B., Wang, C., Ge, G., Wang, S., Niu, F., Zhang, H., & Wang, W. (2026). Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.18052
How many times has this paper been cited?
1 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?
Bofan Xie, Chaokun Wang, Guanchen Ge, Songyao Wang, Fang Niu, Hang Zhang, Wei Wang.
What is the DOI of this paper?
10.48550/arxiv.2610.18052, permanently at https://doi.org/10.48550/arxiv.2610.18052. 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.