@inproceedings{gu-etal-2026-damg,
title = "{DAMG}-{RAG}: Document-Aware Multi-Granularity {RAG} for Visually Rich Document Understanding",
author = "Gu, Jiahao and
Liu, Ningjing and
Ding, Yuanzhuo and
Chen, Siheng",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.71/",
pages = "1541--1560",
ISBN = "979-8-89176-439-2",
abstract = "Real-world documents are visually rich and structurally organized, with text, tables, figures, and captions interleaved across pages. Although retrieval-augmented generation (RAG) is widely used for document question answering, existing pipelines often treat such documents as fixed page- or chunk-level collections. This document-agnostic construction either dilutes evidence in dense pages or fragments semantically related layout elements. Moreover, cross-page questions often require iterative evidence exploration, but existing systems typically follow fixed retrieval paths that do not adapt to the evidence already found.\par We propose DAMG-RAG, a Document-Aware Multi-Granularity RAG framework for visually rich document understanding. During ingestion, DAMG-RAG constructs layout-aware atomic retrieval units and links them to page- and section-level nodes, forming a multi-granularity document tree. During inference, a state-aware agentic workflow maintains explored regions and validated evidence, dynamically selecting exploration and navigation tools over this tree. On MMLongBench, DAMG-RAG obtains 64.7{\%} accuracy with Claude Sonnet 4.6, yielding a 3.6-point gain over the best-performing agentic baseline in our experiments while using 18.8{\%} of its token budget."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2026-damg">
<titleInfo>
<title>DAMG-RAG: Document-Aware Multi-Granularity RAG for Visually Rich Document Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiahao</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ningjing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanzhuo</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siheng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Real-world documents are visually rich and structurally organized, with text, tables, figures, and captions interleaved across pages. Although retrieval-augmented generation (RAG) is widely used for document question answering, existing pipelines often treat such documents as fixed page- or chunk-level collections. This document-agnostic construction either dilutes evidence in dense pages or fragments semantically related layout elements. Moreover, cross-page questions often require iterative evidence exploration, but existing systems typically follow fixed retrieval paths that do not adapt to the evidence already found.\par We propose DAMG-RAG, a Document-Aware Multi-Granularity RAG framework for visually rich document understanding. During ingestion, DAMG-RAG constructs layout-aware atomic retrieval units and links them to page- and section-level nodes, forming a multi-granularity document tree. During inference, a state-aware agentic workflow maintains explored regions and validated evidence, dynamically selecting exploration and navigation tools over this tree. On MMLongBench, DAMG-RAG obtains 64.7% accuracy with Claude Sonnet 4.6, yielding a 3.6-point gain over the best-performing agentic baseline in our experiments while using 18.8% of its token budget.</abstract>
<identifier type="citekey">gu-etal-2026-damg</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.71/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1541</start>
<end>1560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DAMG-RAG: Document-Aware Multi-Granularity RAG for Visually Rich Document Understanding
%A Gu, Jiahao
%A Liu, Ningjing
%A Ding, Yuanzhuo
%A Chen, Siheng
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F gu-etal-2026-damg
%X Real-world documents are visually rich and structurally organized, with text, tables, figures, and captions interleaved across pages. Although retrieval-augmented generation (RAG) is widely used for document question answering, existing pipelines often treat such documents as fixed page- or chunk-level collections. This document-agnostic construction either dilutes evidence in dense pages or fragments semantically related layout elements. Moreover, cross-page questions often require iterative evidence exploration, but existing systems typically follow fixed retrieval paths that do not adapt to the evidence already found.\par We propose DAMG-RAG, a Document-Aware Multi-Granularity RAG framework for visually rich document understanding. During ingestion, DAMG-RAG constructs layout-aware atomic retrieval units and links them to page- and section-level nodes, forming a multi-granularity document tree. During inference, a state-aware agentic workflow maintains explored regions and validated evidence, dynamically selecting exploration and navigation tools over this tree. On MMLongBench, DAMG-RAG obtains 64.7% accuracy with Claude Sonnet 4.6, yielding a 3.6-point gain over the best-performing agentic baseline in our experiments while using 18.8% of its token budget.
%U https://aclanthology.org/2026.aacl-long.71/
%P 1541-1560
Markdown (Informal)
[DAMG-RAG: Document-Aware Multi-Granularity RAG for Visually Rich Document Understanding](https://aclanthology.org/2026.aacl-long.71/) (Gu et al., AACL-IJCNLP 2026)
ACL
- Jiahao Gu, Ningjing Liu, Yuanzhuo Ding, and Siheng Chen. 2026. DAMG-RAG: Document-Aware Multi-Granularity RAG for Visually Rich Document Understanding. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1541–1560, Hengqin, China. Association for Computational Linguistics.