<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bagheri-nezhad-etal-2026-symcode">
    <titleInfo>
        <title>SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sina</namePart>
        <namePart type="family">Bagheri Nezhad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ameeta</namePart>
        <namePart type="family">Agrawal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within this unreliable medium, lacking a mechanism for deterministic verification. To address these limitations, we introduce SymCode, a neurosymbolic framework that reframes mathematical problem-solving as a task of verifiable code generation using the SymPy library. We evaluate SymCode on challenging benchmarks, including MATH-500 and OlympiadBench, demonstrating significant accuracy improvements of up to 13.6 percentage points over baselines. Our analysis shows that SymCode is not only more token-efficient but also fundamentally shifts model failures from opaque logical fallacies towards transparent, programmatic errors. By grounding LLM reasoning in a deterministic symbolic engine, SymCode represents a key step towards more accurate and trustworthy AI in formal domains.</abstract>
    <identifier type="citekey">bagheri-nezhad-etal-2026-symcode</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.76/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>1489</start>
            <end>1503</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation
%A Bagheri Nezhad, Sina
%A Li, Yao
%A Agrawal, Ameeta
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F bagheri-nezhad-etal-2026-symcode
%X Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within this unreliable medium, lacking a mechanism for deterministic verification. To address these limitations, we introduce SymCode, a neurosymbolic framework that reframes mathematical problem-solving as a task of verifiable code generation using the SymPy library. We evaluate SymCode on challenging benchmarks, including MATH-500 and OlympiadBench, demonstrating significant accuracy improvements of up to 13.6 percentage points over baselines. Our analysis shows that SymCode is not only more token-efficient but also fundamentally shifts model failures from opaque logical fallacies towards transparent, programmatic errors. By grounding LLM reasoning in a deterministic symbolic engine, SymCode represents a key step towards more accurate and trustworthy AI in formal domains.
%U https://aclanthology.org/2026.findings-eacl.76/
%P 1489-1503

Markdown (Informal)

[SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation](https://aclanthology.org/2026.findings-eacl.76/) (Bagheri Nezhad et al., Findings 2026)

• SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation (Bagheri Nezhad et al., Findings 2026)

ACL

• Sina Bagheri Nezhad, Yao Li, and Ameeta Agrawal. 2026. SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation. In Findings of the Association for Computational Linguistics: EACL 2026, pages 1489–1503, Rabat, Morocco. Association for Computational Linguistics.