<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-vulagent">
    <titleInfo>
        <title>VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ziliang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ge</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jia</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhi</namePart>
        <namePart type="family">Jin</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</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, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Vulnerability detection with language models is challenging: it requires (i) precisely localizing security-sensitive code and (ii) reasoning about potential vulnerability conditions under complex, partially observed program context. We present VulAgent, a multi-agent vulnerability detection framework based on hypothesis validation. Our design is inspired by how human auditors review code: when noticing a sensitive operation, they form a hypothesis about a possible vulnerability, consider potential trigger paths, and then verify the hypothesis against the project context. Given a code unit, VulAgent first applies multi-view analyzers to identify and localize security-sensitive operations from complementary perspectives. For each sensitive operation, it then constructs an explicit vulnerability hypothesis—including triggering (or exploitation) preconditions and a candidate trigger path—and validates the hypothesis using project context together with the model’s general knowledge of commonly used APIs and security patterns. This validation-oriented design reduces speculative reports and substantially lowers false positives. Across PrimeVul and SVEN, VulAgent improves accuracy by 6.6 percentage points on average, increases vulnerable–fixed pair identification by up to 4.5x (2.46x on average), and reduces false positive rate by 36% relative to recent LLM-based baselines.</abstract>
    <identifier type="citekey">wang-etal-2026-vulagent</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.928/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>18598</start>
            <end>18616</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection
%A Wang, Ziliang
%A Li, Ge
%A Li, Jia
%A Zhu, Hao
%A Jin, Zhi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wang-etal-2026-vulagent
%X Vulnerability detection with language models is challenging: it requires (i) precisely localizing security-sensitive code and (ii) reasoning about potential vulnerability conditions under complex, partially observed program context. We present VulAgent, a multi-agent vulnerability detection framework based on hypothesis validation. Our design is inspired by how human auditors review code: when noticing a sensitive operation, they form a hypothesis about a possible vulnerability, consider potential trigger paths, and then verify the hypothesis against the project context. Given a code unit, VulAgent first applies multi-view analyzers to identify and localize security-sensitive operations from complementary perspectives. For each sensitive operation, it then constructs an explicit vulnerability hypothesis—including triggering (or exploitation) preconditions and a candidate trigger path—and validates the hypothesis using project context together with the model’s general knowledge of commonly used APIs and security patterns. This validation-oriented design reduces speculative reports and substantially lowers false positives. Across PrimeVul and SVEN, VulAgent improves accuracy by 6.6 percentage points on average, increases vulnerable–fixed pair identification by up to 4.5x (2.46x on average), and reduces false positive rate by 36% relative to recent LLM-based baselines.
%U https://aclanthology.org/2026.findings-acl.928/
%P 18598-18616

Markdown (Informal)

[VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection](https://aclanthology.org/2026.findings-acl.928/) (Wang et al., Findings 2026)

• VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection (Wang et al., Findings 2026)

ACL

• Ziliang Wang, Ge Li, Jia Li, Hao Zhu, and Zhi Jin. 2026. VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection. In Findings of the Association for Computational Linguistics: ACL 2026, pages 18598–18616, San Diego, California, United States. Association for Computational Linguistics.