@inproceedings{yang-etal-2026-finmragbench,
title = "{F}in{MRAGB}ench: A Realistic and Complex Benchmark for Multi-Modal {RAG} in Financial Document Analysis",
author = "Yang, Shouqing and
Zhang, Qi and
Yang, Yuhang and
Xu, Ruikang and
Hou, Yuwei and
Jia, Zhulin and
Gao, Lirong and
Wang, Haobo and
Chen, Jinglei and
Wang, Jiexiang and
Guo, Sheng and
Zheng, Bo and
Chen, Gang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.187/",
pages = "3822--3867",
ISBN = "979-8-89176-395-1",
abstract = "Retrieval-augmented generation (RAG) has become a widely adopted paradigm for realistic financial analysis over financial documents. However, existing benchmarks fail to capture realistic financial analysis settings that involve cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. To address this gap, we introduce $\textbf{FinMRAGBench}$, a comprehensive multi-modal financial RAG benchmark in which most questions require retrieving evidence scattered across multiple pages and documents, constructed from large-scale real-world annual reports and comprising 887 expert-verified QA pairs spanning five representative financial analysis tasks. Moreover, we introduce $\textbf{FinMRAGAgent}$, an agent trained on high-quality agentic trajectories following the reasoning-and-acting (ReAct) paradigm, capable of dynamic tool invocation and multi-step financial analysis. Our extensive experiments show that current multi-modal RAG systems still struggle with incomplete retrieval and complex financial reasoning. In contrast, FinMRAGAgent achieves the strongest overall performance across all models, demonstrating that our structured reasoning approach significantly enhances multi-modal RAG in realistic financial scenarios. The code and data are available at https://github.com/sqyangit/FinMRAGBench."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-finmragbench">
<titleInfo>
<title>FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shouqing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruikang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuwei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhulin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lirong</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haobo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinglei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiexiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Chen</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>Retrieval-augmented generation (RAG) has become a widely adopted paradigm for realistic financial analysis over financial documents. However, existing benchmarks fail to capture realistic financial analysis settings that involve cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. To address this gap, we introduce FinMRAGBench, a comprehensive multi-modal financial RAG benchmark in which most questions require retrieving evidence scattered across multiple pages and documents, constructed from large-scale real-world annual reports and comprising 887 expert-verified QA pairs spanning five representative financial analysis tasks. Moreover, we introduce FinMRAGAgent, an agent trained on high-quality agentic trajectories following the reasoning-and-acting (ReAct) paradigm, capable of dynamic tool invocation and multi-step financial analysis. Our extensive experiments show that current multi-modal RAG systems still struggle with incomplete retrieval and complex financial reasoning. In contrast, FinMRAGAgent achieves the strongest overall performance across all models, demonstrating that our structured reasoning approach significantly enhances multi-modal RAG in realistic financial scenarios. The code and data are available at https://github.com/sqyangit/FinMRAGBench.</abstract>
<identifier type="citekey">yang-etal-2026-finmragbench</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.187/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3822</start>
<end>3867</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis
%A Yang, Shouqing
%A Zhang, Qi
%A Yang, Yuhang
%A Xu, Ruikang
%A Hou, Yuwei
%A Jia, Zhulin
%A Gao, Lirong
%A Wang, Haobo
%A Chen, Jinglei
%A Wang, Jiexiang
%A Guo, Sheng
%A Zheng, Bo
%A Chen, Gang
%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 yang-etal-2026-finmragbench
%X Retrieval-augmented generation (RAG) has become a widely adopted paradigm for realistic financial analysis over financial documents. However, existing benchmarks fail to capture realistic financial analysis settings that involve cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. To address this gap, we introduce FinMRAGBench, a comprehensive multi-modal financial RAG benchmark in which most questions require retrieving evidence scattered across multiple pages and documents, constructed from large-scale real-world annual reports and comprising 887 expert-verified QA pairs spanning five representative financial analysis tasks. Moreover, we introduce FinMRAGAgent, an agent trained on high-quality agentic trajectories following the reasoning-and-acting (ReAct) paradigm, capable of dynamic tool invocation and multi-step financial analysis. Our extensive experiments show that current multi-modal RAG systems still struggle with incomplete retrieval and complex financial reasoning. In contrast, FinMRAGAgent achieves the strongest overall performance across all models, demonstrating that our structured reasoning approach significantly enhances multi-modal RAG in realistic financial scenarios. The code and data are available at https://github.com/sqyangit/FinMRAGBench.
%U https://aclanthology.org/2026.findings-acl.187/
%P 3822-3867
Markdown (Informal)
[FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis](https://aclanthology.org/2026.findings-acl.187/) (Yang et al., Findings 2026)
ACL
- Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, and Gang Chen. 2026. FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis. In Findings of the Association for Computational Linguistics: ACL 2026, pages 3822–3867, San Diego, California, United States. Association for Computational Linguistics.