<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-peng-2026-reason">
    <titleInfo>
        <title>Reason-Code: Reliable Code Generation via Test-Driven Monte Carlo Tree Search</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zixu</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiqi</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) are widely used for code generation, but their performance degrades on tasks requiring multi-step logical reasoning. In practice, reliability is often improved through multi-sample inference, but its cost grows linearly with the sample size, making it impractical under strict latency constraints. To address this, we propose Reason-Code, an inference-time framework that formulates code generation as a search process guided by execution feedback. It integrates Monte Carlo Tree Search (MCTS) with a lightweight execution sandbox, where candidate programs are evaluated via unit tests. To control inference cost, Reason-Code adopts a conditional budgeting strategy that activates search only when greedy generation fails. Compared with large-sample Best-of-N sampling, Reason-Code is designed to improve reliability without paying the full linear cost of additional sampling under strict latency budgets. Experiments on HumanEval and MBPP show that Reason-Code matches strong sampling baselines (e.g., Best-of-10) with lower token cost and no regression. Additional matched-budget analyses show that execution-guided adaptive inference improves over independent sampling/filtering baselines, while differences between UCB-guided search and simpler iterative repair are limited at low budget.</abstract>
    <identifier type="citekey">li-peng-2026-reason</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.30/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>447</start>
            <end>458</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reason-Code: Reliable Code Generation via Test-Driven Monte Carlo Tree Search
%A Li, Zixu
%A Peng, Zhiqi
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F li-peng-2026-reason
%X Large Language Models (LLMs) are widely used for code generation, but their performance degrades on tasks requiring multi-step logical reasoning. In practice, reliability is often improved through multi-sample inference, but its cost grows linearly with the sample size, making it impractical under strict latency constraints. To address this, we propose Reason-Code, an inference-time framework that formulates code generation as a search process guided by execution feedback. It integrates Monte Carlo Tree Search (MCTS) with a lightweight execution sandbox, where candidate programs are evaluated via unit tests. To control inference cost, Reason-Code adopts a conditional budgeting strategy that activates search only when greedy generation fails. Compared with large-sample Best-of-N sampling, Reason-Code is designed to improve reliability without paying the full linear cost of additional sampling under strict latency budgets. Experiments on HumanEval and MBPP show that Reason-Code matches strong sampling baselines (e.g., Best-of-10) with lower token cost and no regression. Additional matched-budget analyses show that execution-guided adaptive inference improves over independent sampling/filtering baselines, while differences between UCB-guided search and simpler iterative repair are limited at low budget.
%U https://aclanthology.org/2026.acl-industry.30/
%P 447-458

Markdown (Informal)

[Reason-Code: Reliable Code Generation via Test-Driven Monte Carlo Tree Search](https://aclanthology.org/2026.acl-industry.30/) (Li & Peng, ACL 2026)

• Reason-Code: Reliable Code Generation via Test-Driven Monte Carlo Tree Search (Li & Peng, ACL 2026)

ACL

• Zixu Li and Zhiqi Peng. 2026. Reason-Code: Reliable Code Generation via Test-Driven Monte Carlo Tree Search. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 447–458, San Diego, California, USA. Association for Computational Linguistics.