<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khatri-2026-context">
    <titleInfo>
        <title>Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Prakhar</namePart>
        <namePart type="family">Khatri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Persistent context files (AGENTS.md, CLAUDE.md) 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, and 288 evaluated runs with gold-test evaluation. Context strategy does not measurably move correctness on either agent (bounded to łeq10–15pp via equivalence testing). A failure-mode triage reveals why: agents fail on implementation skill—feature design, pattern selection, exact wiring—not missing repository knowledge that a context file could supply; a manipulation probe confirms the real AGENTS.md never converts a near-miss to a pass on either agent. We further show that borderline task difficulty is agent-specific (Spearman ρ=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.</abstract>
    <identifier type="citekey">khatri-2026-context</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.5/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>57</start>
            <end>67</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories
%A Khatri, Prakhar
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F khatri-2026-context
%X Persistent context files (AGENTS.md, CLAUDE.md) 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, and 288 evaluated runs with gold-test evaluation. Context strategy does not measurably move correctness on either agent (bounded to łeq10–15pp via equivalence testing). A failure-mode triage reveals why: agents fail on implementation skill—feature design, pattern selection, exact wiring—not missing repository knowledge that a context file could supply; a manipulation probe confirms the real AGENTS.md never converts a near-miss to a pass on either agent. We further show that borderline task difficulty is agent-specific (Spearman ρ=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.
%U https://aclanthology.org/2026.realm-1.5/
%P 57-67

Markdown (Informal)

[Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories](https://aclanthology.org/2026.realm-1.5/) (Khatri, REALM 2026)

• Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories (Khatri, REALM 2026)

ACL

• Prakhar Khatri. 2026. Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 57–67, Budapest, Hungary. Association for Computational Linguistics.