Preprint · 2026 · Open access
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents
arXiv (Cornell University) · Published 23 July 2026 · DOI 10.48550/arxiv.2607.20972
In brief
“Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents” is a 2026 preprint by Swapnanil Saha, 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
- 26
- Authors
- 1
Abstract
Coding agents ship with one kind of memory: documents. Instruction files, plan artifacts, and auto-written memory directories are deliberately authored and deliberately retrieved: the agent must choose to write them and choose to read them back. Human expertise runs on a second tier that never gets written down: situationally-bound operational facts (gotchas, locations, local conventions) encoded as a side effect of the work and retrieved involuntarily when the situation cues them. We argue this second tier is the load-bearing one for long-running agents and must be a harness property, not an agent choice. We contribute: (1) a two-tier design theory grounded in the cognitive literature on memory offloading, incidental encoding, and event-based prospective memory, each mapped to an architectural requirement; (2) a cue-anchored memory model where memories carry first-class trigger conditions over a composable vocabulary (path, symbol, semantic, event, temporal), evaluated deterministically by the harness, a composition no surveyed academic or shipped system provides; (3) a controlled evaluation on a real coding task showing that voluntary memory use is near zero even with a pre-seeded store (0 memory operations in 114 turns), that deterministic injection delivered in every seeded run with zero false alarms, and that 39% of intra-session re-reads re-buy content paid for before a compaction boundary; (4) a repeated-compaction decay probe: ten facts held only in conversation vanish at the first summary and stay absent from 106 of 108 compactions, and the deprived agent greps the harness's own session files to rebuild them, while the same facts injected from a harness-owned store arrive intact through all 138 compact-resumes as the final summary carries none. Delivery, not storage, is the product: the reliable memory channel for agents is the one the agent never has to think about.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Saha, S. (2026). Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.20972
MLA 9
Saha, Swapnanil. “Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2607.20972.
Chicago
Saha, Swapnanil. 2026. “Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.20972.
Harvard
Saha, S. (2026) ‘Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2607.20972.
IEEE
S. Saha, “Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2607.20972.
BibTeX
@misc{saha2026delivery,
title = {{Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents}},
author = {Saha, Swapnanil},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2607.20972},
url = {https://doi.org/10.48550/arxiv.2607.20972}
}
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
- coding agents
- large language models
- working memory
- memory offloading
- incidental encoding
- prospective memory
- memory compaction
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?
Saha, S. (2026). Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2607.20972
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?
Swapnanil Saha.
What is the DOI of this paper?
10.48550/arxiv.2607.20972, permanently at https://doi.org/10.48550/arxiv.2607.20972. 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.