<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-lin-2026-contract">
    <titleInfo>
        <title>Contract Before Code: Failure-Compiled Contracts for Long-Horizon Coding Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiangnan</namePart>
        <namePart type="family">YU</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kisson</namePart>
        <namePart type="given">Songqi</namePart>
        <namePart type="family">Lin</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>Long-horizon coding agents can make many edits before testing a task-wide assumption about an API, authentication mode, environment, or persistent state. A late verifier then exposes that the implementation rests on a false premise. We call the missing step contract acquisition and propose Contract Before Code (CBC), harness-level middleware that compiles historical failures into executable preflight gates. CBC normalizes trajectories, extracts recurring failure signatures, and compiles contracts containing an applicability condition, a probe template, and a planning consequence. At inference time, it retrieves applicable contracts and runs instantiated probes before broad implementation work. Among 1,421 parsed failed SWE-Marathon trajectories, weak labels identify candidate rates of 2.6% overall and 17.5% on stripe-clone; these are not root-cause prevalence estimates. A 120-trajectory human audit reports 76.3% contract precision and 71.4% executable-probe synthesis. Across four service/API-clone tasks and 32 runs per method, CBC achieves 31.3% success (95% CI 18.0–48.6), an observed 21.9-percentage-point increase over vanilla, with 55.6% fewer pre-verification edits at 1.11× normalized token cost. The small end-to-end study supports preliminary within-family benefits; broader transfer and the stability of these gains remain unestablished.</abstract>
    <identifier type="citekey">yu-lin-2026-contract</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.72/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1032</start>
            <end>1041</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Contract Before Code: Failure-Compiled Contracts for Long-Horizon Coding Agents
%A YU, Jiangnan
%A Lin, Kisson Songqi
%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 yu-lin-2026-contract
%X Long-horizon coding agents can make many edits before testing a task-wide assumption about an API, authentication mode, environment, or persistent state. A late verifier then exposes that the implementation rests on a false premise. We call the missing step contract acquisition and propose Contract Before Code (CBC), harness-level middleware that compiles historical failures into executable preflight gates. CBC normalizes trajectories, extracts recurring failure signatures, and compiles contracts containing an applicability condition, a probe template, and a planning consequence. At inference time, it retrieves applicable contracts and runs instantiated probes before broad implementation work. Among 1,421 parsed failed SWE-Marathon trajectories, weak labels identify candidate rates of 2.6% overall and 17.5% on stripe-clone; these are not root-cause prevalence estimates. A 120-trajectory human audit reports 76.3% contract precision and 71.4% executable-probe synthesis. Across four service/API-clone tasks and 32 runs per method, CBC achieves 31.3% success (95% CI 18.0–48.6), an observed 21.9-percentage-point increase over vanilla, with 55.6% fewer pre-verification edits at 1.11× normalized token cost. The small end-to-end study supports preliminary within-family benefits; broader transfer and the stability of these gains remain unestablished.
%U https://aclanthology.org/2026.realm-1.72/
%P 1032-1041

Markdown (Informal)

[Contract Before Code: Failure-Compiled Contracts for Long-Horizon Coding Agents](https://aclanthology.org/2026.realm-1.72/) (YU & Lin, REALM 2026)

• Contract Before Code: Failure-Compiled Contracts for Long-Horizon Coding Agents (YU & Lin, REALM 2026)

ACL

• Jiangnan YU and Kisson Songqi Lin. 2026. Contract Before Code: Failure-Compiled Contracts for Long-Horizon Coding Agents. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1032–1041, Budapest, Hungary. Association for Computational Linguistics.