@inproceedings{qi-etal-2026-datacross,
title = "{D}ata{C}ross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis",
author = "Qi, Ruyi and
Liu, Zhou and
Gu, Yang and
Su, Zeli and
Zewei, Pan and
Chen, Xing and
Song, Yuanfeng and
Wangxiaoyue and
Zhang, Wentao",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1229/",
pages = "26006--26027",
ISBN = "979-8-89176-462-0",
abstract = "Real-world analysis often requires combining directly queryable structured sources (e.g., SQL and CSV) with evidence preserved only in visual documents, such as scanned reports, invoices, and dashboards. Current analytics agents still focus primarily on structured and textual inputs, leaving this cross-modal setting underexplored. We introduce DataCross, a benchmark and agent framework for heterogeneous, insight-driven data analysis. DataCrossBench contains 200 end-to-end tasks across six fine-grained categories: Fund Analysis, FinTech, Internet Development, Internet Firms, Short-form Drama, and AI Healthcare, grouped into four macro sectors and mixing SQL/CSV/JSON/TXT sources with image-based evidence. The benchmark is built with a human-in-the-loop reverse-synthesis pipeline to preserve cross-source dependency while keeping the target insights verifiable. We further propose DataCrossAgent, which coordinates source-specialized agents through intra-source exploration, source prioritization, cross-source pollination, and Reasoning ReAct (reReAct)-based executable verification. Experiments show that DataCrossBench reveals a difficulty gap for most baselines, especially on vision-dependent Hard tasks, and that DataCrossAgent improves average factuality over vanilla GPT-4o from 0.3291 to 0.4270 (+29.7{\%}) while showing a smaller Easy-to-Hard degradation than several baselines. These results position DataCrossBench as a practical testbed for cross-modal heterogeneous data analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2026-datacross">
<titleInfo>
<title>DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruyi</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeli</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pan</namePart>
<namePart type="family">Zewei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanfeng</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Wangxiaoyue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wentao</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>Real-world analysis often requires combining directly queryable structured sources (e.g., SQL and CSV) with evidence preserved only in visual documents, such as scanned reports, invoices, and dashboards. Current analytics agents still focus primarily on structured and textual inputs, leaving this cross-modal setting underexplored. We introduce DataCross, a benchmark and agent framework for heterogeneous, insight-driven data analysis. DataCrossBench contains 200 end-to-end tasks across six fine-grained categories: Fund Analysis, FinTech, Internet Development, Internet Firms, Short-form Drama, and AI Healthcare, grouped into four macro sectors and mixing SQL/CSV/JSON/TXT sources with image-based evidence. The benchmark is built with a human-in-the-loop reverse-synthesis pipeline to preserve cross-source dependency while keeping the target insights verifiable. We further propose DataCrossAgent, which coordinates source-specialized agents through intra-source exploration, source prioritization, cross-source pollination, and Reasoning ReAct (reReAct)-based executable verification. Experiments show that DataCrossBench reveals a difficulty gap for most baselines, especially on vision-dependent Hard tasks, and that DataCrossAgent improves average factuality over vanilla GPT-4o from 0.3291 to 0.4270 (+29.7%) while showing a smaller Easy-to-Hard degradation than several baselines. These results position DataCrossBench as a practical testbed for cross-modal heterogeneous data analysis.</abstract>
<identifier type="citekey">qi-etal-2026-datacross</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1229/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>26006</start>
<end>26027</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis
%A Qi, Ruyi
%A Liu, Zhou
%A Gu, Yang
%A Su, Zeli
%A Zewei, Pan
%A Chen, Xing
%A Song, Yuanfeng
%A Zhang, Wentao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%A Wangxiaoyue
%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 qi-etal-2026-datacross
%X Real-world analysis often requires combining directly queryable structured sources (e.g., SQL and CSV) with evidence preserved only in visual documents, such as scanned reports, invoices, and dashboards. Current analytics agents still focus primarily on structured and textual inputs, leaving this cross-modal setting underexplored. We introduce DataCross, a benchmark and agent framework for heterogeneous, insight-driven data analysis. DataCrossBench contains 200 end-to-end tasks across six fine-grained categories: Fund Analysis, FinTech, Internet Development, Internet Firms, Short-form Drama, and AI Healthcare, grouped into four macro sectors and mixing SQL/CSV/JSON/TXT sources with image-based evidence. The benchmark is built with a human-in-the-loop reverse-synthesis pipeline to preserve cross-source dependency while keeping the target insights verifiable. We further propose DataCrossAgent, which coordinates source-specialized agents through intra-source exploration, source prioritization, cross-source pollination, and Reasoning ReAct (reReAct)-based executable verification. Experiments show that DataCrossBench reveals a difficulty gap for most baselines, especially on vision-dependent Hard tasks, and that DataCrossAgent improves average factuality over vanilla GPT-4o from 0.3291 to 0.4270 (+29.7%) while showing a smaller Easy-to-Hard degradation than several baselines. These results position DataCrossBench as a practical testbed for cross-modal heterogeneous data analysis.
%U https://aclanthology.org/2026.findings-emnlp.1229/
%P 26006-26027
Markdown (Informal)
[DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis](https://aclanthology.org/2026.findings-emnlp.1229/) (Qi et al., Findings 2026)
ACL
- Ruyi Qi, Zhou Liu, Yang Gu, Zeli Su, Pan Zewei, Xing Chen, Yuanfeng Song, Wangxiaoyue, and Wentao Zhang. 2026. DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 26006–26027, Budapest, Hungary. Association for Computational Linguistics.