[2607.27250] Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Software Engineering

arXiv:2607.27250 (cs)

[Submitted on 28 Jul 2026]

Title:Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories

Authors:Prakhar Khatri<br>View a PDF of the paper titled Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories, by Prakhar Khatri

View PDF<br>HTML (experimental)

Abstract:Persistent context files (this http URL, this http URL) are standard practice for guiding AI coding agents, yet evidence for their effectiveness is contradictory. We present a controlled ablation of context-injection strategy across two frontier agents (Claude Code and Codex), 17 real tasks from 3 repositories (15 shared + 2 Codex-only), and 288 evaluated runs with gold-test evaluation. Context strategy does not measurably move correctness on either agent (bounded to this http URL never converts a near-miss to a pass on either agent. We further show that borderline task difficulty is agent-specific (Spearman rho=0.75), offering a candidate explanation for prior contradictions: single-agent studies draw tasks from different agents' informative bands. We release all code, data, and analysis.

Subjects:

Software Engineering (cs.SE); Artificial Intelligence (cs.AI)

Cite as:<br>arXiv:2607.27250 [cs.SE]

(or<br>arXiv:2607.27250v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2607.27250

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Prakhar Khatri [view email]<br>[v1]<br>Tue, 28 Jul 2026 11:07:53 UTC (51 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories, by Prakhar Khatri<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.SE

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.AI

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