[2608.02376] Token-Native Storage: Read and Write in your Agent's Language

Skip to main content

System maintenance August 4th and 5th<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Databases

arXiv:2608.02376 (cs)

[Submitted on 3 Aug 2026]

Title:Token-Native Storage: Read and Write in your Agent's Language

Authors:Kumar Shivendu<br>View a PDF of the paper titled Token-Native Storage: Read and Write in your Agent's Language, by Kumar Shivendu

View PDF<br>HTML (experimental)

Abstract:Search and database engines still store text as UTF-8, a format built for humans. But the systems that increasingly read and write that text (embedders, rerankers, and language-model agents) work in token IDs, not characters, so every access pays to translate between the two. As agents become the primary readers and writers of stored text, we argue for token-native storage: keep the text as the model's own byte-pair-encoding (BPE) token IDs. This is both smaller and faster. Packing r50k IDs as uint16 already beats UTF-8 by 2.25x on English with no compression, and an entropy coder reaches 3.30x. Across six tokenizers and three corpora (English, code, Hindi), compressing token IDs matches or beats every byte codec, even a corpus-trained zstd dictionary. Two findings sharpen the case. BPE numbers tokens by merge order, not frequency, and re-ranking by frequency lets a plain integer codec (streamvbyte) recover most of the entropy coder's ratio while decoding ~7x faster, a one-line change we ask AI labs to make when they publish vocabularies. And because a model reads token IDs, not text, a token-native store hands them over directly instead of re-tokenizing on every read, ~10-600x faster. The only barrier is that sharing token IDs requires a common tokenizer, which is not always true across model families yet, so we argue for standardization: a published, shared vocabulary, the way ASCII and UTF-8 standardized text.

Comments:<br>11 pages, 5 figures, 2 tables

Subjects:

Databases (cs.DB); Computation and Language (cs.CL); Information Retrieval (cs.IR)

ACM classes:<br>E.4; H.2.4; H.3.3; I.2.7

Cite as:<br>arXiv:2608.02376 [cs.DB]

(or<br>arXiv:2608.02376v1 [cs.DB] for this version)

https://doi.org/10.48550/arXiv.2608.02376

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Kumar Shivendu [view email]<br>[v1]<br>Mon, 3 Aug 2026 15:20:36 UTC (395 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Token-Native Storage: Read and Write in your Agent's Language, by Kumar Shivendu<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.DB

next >

new<br>recent<br>| 2026-08

Change to browse by:

cs<br>cs.CL<br>cs.IR

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from