Preprint · 2026 · Open access
Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It
arXiv (Cornell University) · Published 3 October 2026 · DOI 10.48550/arxiv.2610.04794
In brief
“Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It” is a 2026 preprint by Ansuman Mullick and Eray Tüzün, published in arXiv (Cornell University). OpenAlex counts 0 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
- 0
- References
- 5
- Authors
- 2
Abstract
An agent with long-term memory can answer from a record it should no longer use, such as a plan the user later cancelled. We ask what a memory store must expose for an agent to know this before retrieving anything, and we score that judgment on its own, as metamemory monitoring. Readers see only a value-free summary: record counts by lifecycle state and a list of attribute names. Each of 148 questions is asked against three versions of one store that differ in one attribute, so wording cannot give the answer away. What a model adds depends on the length of that list. On the short lists the benchmark's ground truth produces (2.6 names on average), none of five language models reliably beats a cosine-similarity lookup over the names, and the three stronger ones are equivalent to it within 0.05. Under a control that fixes counts and list length, none is reliably above it and none is shown equivalent. On lists longer than the stores we tested write, padded to 60 names, the lookup loses 0.18; GPT-5.6 Luna and Sol lose 0.06 to 0.07 and lead it by 0.13 to 0.14, while the other three fall with it. The lead holds for Sol against a sibling padded to the same length and counts. Reworded to share no word with the names, the lookup loses 0.02 and one stronger reader edges 0.04 ahead. On the short lists the three stronger readers lead only where the summary counts a state without naming it, and one count feature closes that lead within a question, though not when items are pooled. The backends we tested omit or misstate this information: under FR-Bank's own metadata, GPT-4.1 mini, Haiku 4.5 and the lookup fall from 0.73, 0.82 and 0.75 to 0.60, 0.71 and 0.59. In these tests, what the store wrote down limited every reader we gave it to. All stores are synthetic; control, whether a better judgment yields a better answer, is left to a later study.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Mullick, A., & Tüzün, E. (2026). Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.04794
MLA 9
Mullick, Ansuman, and Eray Tüzün. “Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.04794.
Chicago
Mullick, Ansuman and Eray Tüzün. 2026. “Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.04794.
Harvard
Mullick, A. and Tüzün, E. (2026) ‘Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It’, arXiv (Cornell University). doi:10.48550/arxiv.2610.04794.
IEEE
A. Mullick and E. Tüzün, “Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.04794.
BibTeX
@misc{mullick2026knowing,
title = {{Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It}},
author = {Mullick, Ansuman and Tüzün, Eray},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2610.04794},
url = {https://doi.org/10.48550/arxiv.2610.04794}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- metamemory monitoring
- memory retrieval
- GPT-4
- GPT-5
- haiku
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?
Mullick, A., & Tüzün, E. (2026). Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.04794
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?
Ansuman Mullick, Eray Tüzün.
What is the DOI of this paper?
10.48550/arxiv.2610.04794, permanently at https://doi.org/10.48550/arxiv.2610.04794. 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.