<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-bizsage">
    <titleInfo>
        <title>BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuhe</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guangyu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiaxin</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guang</namePart>
        <namePart type="family">Zhang</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>While multi-agent systems based on large language models (LLMs) have shown promise in automating academic research workflows, extending them to economics and business research presents two key challenges, as specialized domain knowledge often spans neighboring disciplines yet remains difficult to access in a structured manner. First, existing methods primarily retrieve information at the paper level, whereas the evidence required for research tasks is often distributed across different sections, creating a granularity mismatch that limits retrieval coverage and precision. Second, these fields demand strict empirical rigor, yet current systems provide limited mechanisms for learning from evaluation feedback. We present BizSage, a multi-agent framework that combines corpus-level fine-grained retrieval with quality-driven self-evolution. We construct a Lateral Knowledge Graph (LKG) by integrating section-level knowledge graphs and apply Personalized PageRank (PPR) to identify sections that are both semantically relevant and structurally important. Seven specialized agents collaborate under a Meta-Review self-evolution mechanism that distills failure modes from evaluation traces into reusable strategies. On a benchmark spanning four domains and three tasks, BizSage ranks first on the majority of metrics, achieves pairwise win rates above 60% against six baselines, and produces zero hallucinated citations. We hope BizSage paves the way for reliable research assistance in economics, business, and the broader social sciences.</abstract>
    <identifier type="citekey">wu-etal-2026-bizsage</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.354/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>7399</start>
            <end>7429</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval
%A Wu, Yuhe
%A Wang, Guangyu
%A Liu, Jiaxin
%A Zhang, Guang
%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 wu-etal-2026-bizsage
%X While multi-agent systems based on large language models (LLMs) have shown promise in automating academic research workflows, extending them to economics and business research presents two key challenges, as specialized domain knowledge often spans neighboring disciplines yet remains difficult to access in a structured manner. First, existing methods primarily retrieve information at the paper level, whereas the evidence required for research tasks is often distributed across different sections, creating a granularity mismatch that limits retrieval coverage and precision. Second, these fields demand strict empirical rigor, yet current systems provide limited mechanisms for learning from evaluation feedback. We present BizSage, a multi-agent framework that combines corpus-level fine-grained retrieval with quality-driven self-evolution. We construct a Lateral Knowledge Graph (LKG) by integrating section-level knowledge graphs and apply Personalized PageRank (PPR) to identify sections that are both semantically relevant and structurally important. Seven specialized agents collaborate under a Meta-Review self-evolution mechanism that distills failure modes from evaluation traces into reusable strategies. On a benchmark spanning four domains and three tasks, BizSage ranks first on the majority of metrics, achieves pairwise win rates above 60% against six baselines, and produces zero hallucinated citations. We hope BizSage paves the way for reliable research assistance in economics, business, and the broader social sciences.
%U https://aclanthology.org/2026.findings-emnlp.354/
%P 7399-7429

Markdown (Informal)

[BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval](https://aclanthology.org/2026.findings-emnlp.354/) (Wu et al., Findings 2026)

• BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval (Wu et al., Findings 2026)

ACL

• Yuhe Wu, Guangyu Wang, Jiaxin Liu, and Guang Zhang. 2026. BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 7399–7429, Budapest, Hungary. Association for Computational Linguistics.