<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trirat-etal-2026-multimodal">
    <titleInfo>
        <title>Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Patara</namePart>
        <namePart type="family">Trirat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jin</namePart>
        <namePart type="given">Myung</namePart>
        <namePart type="family">Kwak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jay</namePart>
        <namePart type="family">Heo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heejun</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sung</namePart>
        <namePart type="given">Ju</namePart>
        <namePart type="family">Hwang</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are increasingly used as natural-language interfaces to structured data, yet they remain brittle when reasoning over time series. Visual patterns can be misleading, numerical claims can be hallucinated, and textual context can override evidence from the signal. We study *zero-shot* time-series reasoning as a multimodal evidence arbitration problem for LLM agents. We propose **TS-Debate**, an inference-time multi-agent protocol that requires no task-specific fine-tuning. TS-Debate first elicits relevant domain knowledge, then assigns modality-specialized agents to textual context, visual patterns, and numerical signals, and coordinates their interaction through a verification-conflict-calibration procedure. Reviewer agents check decision-critical claims with lightweight code execution and numerical lookup, resolve cross-modal disagreement, and calibrate the final answer. Unlike generic multi-agent debate or unconstrained tool use, TS-Debate specifies how evidence is exposed, which claims are checkable, and how verification outcomes shape synthesis. Across 20 tasks from three public benchmarks, TS-Debate improves classification and question answering performance over strong baselines, while revealing that debate is most useful for global-structure and cross-view reasoning rather than local value reconstruction.</abstract>
    <identifier type="citekey">trirat-etal-2026-multimodal</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2572/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>58432</start>
            <end>58456</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
%A Trirat, Patara
%A Kwak, Jin Myung
%A Heo, Jay
%A Lee, Heejun
%A Hwang, Sung Ju
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F trirat-etal-2026-multimodal
%X Large language models (LLMs) are increasingly used as natural-language interfaces to structured data, yet they remain brittle when reasoning over time series. Visual patterns can be misleading, numerical claims can be hallucinated, and textual context can override evidence from the signal. We study *zero-shot* time-series reasoning as a multimodal evidence arbitration problem for LLM agents. We propose **TS-Debate**, an inference-time multi-agent protocol that requires no task-specific fine-tuning. TS-Debate first elicits relevant domain knowledge, then assigns modality-specialized agents to textual context, visual patterns, and numerical signals, and coordinates their interaction through a verification-conflict-calibration procedure. Reviewer agents check decision-critical claims with lightweight code execution and numerical lookup, resolve cross-modal disagreement, and calibrate the final answer. Unlike generic multi-agent debate or unconstrained tool use, TS-Debate specifies how evidence is exposed, which claims are checkable, and how verification outcomes shape synthesis. Across 20 tasks from three public benchmarks, TS-Debate improves classification and question answering performance over strong baselines, while revealing that debate is most useful for global-structure and cross-view reasoning rather than local value reconstruction.
%U https://aclanthology.org/2026.emnlp-main.2572/
%P 58432-58456

Markdown (Informal)

[Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning](https://aclanthology.org/2026.emnlp-main.2572/) (Trirat et al., EMNLP 2026)

• Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning (Trirat et al., EMNLP 2026)

ACL

• Patara Trirat, Jin Myung Kwak, Jay Heo, Heejun Lee, and Sung Ju Hwang. 2026. Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 58432–58456, Budapest, Hungary. Association for Computational Linguistics.