<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2026-towards">
    <titleInfo>
        <title>Towards Structured Mechanistic Reasoning in Single-cell Prediction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yunhui</namePart>
        <namePart type="family">Jang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lu</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jake</namePart>
        <namePart type="family">Fawkes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alisandra</namePart>
        <namePart type="given">Kaye</namePart>
        <namePart type="family">Denton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dominique</namePart>
        <namePart type="family">Beaini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emmanuel</namePart>
        <namePart type="family">Noutahi</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their application in open-ended scientific domains such as biology remains limited, largely because they lack factually grounded and actionable explanations. To address this, we introduce a structured explanation formalism for virtual cells that represents biological reasoning as mechanistic action graphs, enabling systematic verification and falsification. Building on this, we propose VCR-Agent, a multi-agent framework that integrates biologically grounded knowledge retrieval with a verifier-based filtering approach to autonomously generate and validate mechanistic reasoning. Using this framework, we release the VC-TRACES dataset, which consists of verified mechanistic explanations derived from the Tahoe-100M atlas. We observed that training with these explanations improves factual precision and provides a more effective supervision signal for downstream gene expression prediction on TahoeQA. These results underscore the importance of reliable mechanistic reasoning for virtual cells, which can be enhanced through the synergy of a multi-agent system and rigorous verification.</abstract>
    <identifier type="citekey">jang-etal-2026-towards</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1394</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1394/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>29659</start>
            <end>29694</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Structured Mechanistic Reasoning in Single-cell Prediction
%A Jang, Yunhui
%A Zhu, Lu
%A Fawkes, Jake
%A Denton, Alisandra Kaye
%A Beaini, Dominique
%A Noutahi, Emmanuel
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F jang-etal-2026-towards
%X Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their application in open-ended scientific domains such as biology remains limited, largely because they lack factually grounded and actionable explanations. To address this, we introduce a structured explanation formalism for virtual cells that represents biological reasoning as mechanistic action graphs, enabling systematic verification and falsification. Building on this, we propose VCR-Agent, a multi-agent framework that integrates biologically grounded knowledge retrieval with a verifier-based filtering approach to autonomously generate and validate mechanistic reasoning. Using this framework, we release the VC-TRACES dataset, which consists of verified mechanistic explanations derived from the Tahoe-100M atlas. We observed that training with these explanations improves factual precision and provides a more effective supervision signal for downstream gene expression prediction on TahoeQA. These results underscore the importance of reliable mechanistic reasoning for virtual cells, which can be enhanced through the synergy of a multi-agent system and rigorous verification.
%R 10.18653/2026.findings-emnlp.1394
%U https://aclanthology.org/2026.findings-emnlp.1394/
%U https://doi.org/10.18653/2026.findings-emnlp.1394
%P 29659-29694

Markdown (Informal)

[Towards Structured Mechanistic Reasoning in Single-cell Prediction](https://aclanthology.org/2026.findings-emnlp.1394/) (Jang et al., Findings 2026)

• Towards Structured Mechanistic Reasoning in Single-cell Prediction (Jang et al., Findings 2026)

ACL

• Yunhui Jang, Lu Zhu, Jake Fawkes, Alisandra Kaye Denton, Dominique Beaini, and Emmanuel Noutahi. 2026. Towards Structured Mechanistic Reasoning in Single-cell Prediction. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 29659–29694, Budapest, Hungary. Association for Computational Linguistics.