[2608.11095] Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Artificial Intelligence

arXiv:2608.11095 (cs)

[Submitted on 11 Aug 2026]

Title:Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding

Authors:Kushal Chakrabarti<br>View a PDF of the paper titled Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding, by Kushal Chakrabarti

View PDF<br>HTML (experimental)

Abstract:Agentic coding READMEs like this http URL grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to imperfect recall: appending an instruction is always cheap, but once an instruction's rationale is gone, deleting it without risking a correctness regression costs O(2^|D|) in a prompt of |D| instructions. We name the resulting divergence catastrophic remembering, the inverse of catastrophic forgetting around which continual learning is organized. First, we characterize this phenomenon across 247,694 instruction lifetimes in 1,867 repositories: agentic prompts grow without bound, more than tripling over their lifetime (+226%), gaining +4.9 net instructions every commit; further, the older an instruction gets, the less likely it is to be deleted (log-hazard -0.032/commit). Then, we show that prompt comments can halt the growth: inverting IFEval yields verifiable worlds whose optimal prompts are known, and there comments encoding latent reasoning remove 99.3% of excess instructions (+211.3% to +1.4%). Finally, applying the same inversion to WildIFEval, we show that prompt comments can improve real-world agentic instruction-following by up to 23.1%. If English is the new code, why don't we have comments yet?

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE)

Cite as:<br>arXiv:2608.11095 [cs.AI]

(or<br>arXiv:2608.11095v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.11095

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Kushal Chakrabarti [view email]<br>[v1]<br>Tue, 11 Aug 2026 16:00:55 UTC (110 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding, by Kushal Chakrabarti<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

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

Change to browse by:

cs<br>cs.LG<br>cs.SE

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