@inproceedings{zhang-etal-2026-agents,
title = "Do Agents Help? Agentic Document Information Extraction with Enterprise Database Grounding",
author = "Zhang, Zhijie and
Shao, Hongxin and
Geiger, Mattis Lennart and
Bai, Tao and
Dahlmeier, Daniel",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.200/",
pages = "3357--3375",
ISBN = "979-8-89176-460-6",
abstract = "In enterprise applications, document information extraction (IE) does not operate in isolation: extracted information must match the systems of record (SoR) for the process to work. While reliable IE demands entity extraction, SoR grounding, and iterative refinement, existing methods rely on single-pass inference. To address this gap, we propose a SoR-grounded agentic pipeline and evaluate four agentic paradigms (Agentic Workflow, ReAct, Plan-Execute-Critic, and Dynamic Agent Collaboration) on real-world enterprise data. We focus on the goods receipt and invoice settlement processes as representative use cases, where delivery notes and invoices must be matched and verified against purchase order SoR. Our results show that agentic approaches generally match or exceed non-agentic baselines, with simpler paradigms matching or outperforming complex alternatives. Paired with systematic error analysis, this work provides actionable guidance for deploying agentic document AI at enterprise scale."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-agents">
<titleInfo>
<title>Do Agents Help? Agentic Document Information Extraction with Enterprise Database Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhijie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongxin</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mattis</namePart>
<namePart type="given">Lennart</namePart>
<namePart type="family">Geiger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Dahlmeier</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>In enterprise applications, document information extraction (IE) does not operate in isolation: extracted information must match the systems of record (SoR) for the process to work. While reliable IE demands entity extraction, SoR grounding, and iterative refinement, existing methods rely on single-pass inference. To address this gap, we propose a SoR-grounded agentic pipeline and evaluate four agentic paradigms (Agentic Workflow, ReAct, Plan-Execute-Critic, and Dynamic Agent Collaboration) on real-world enterprise data. We focus on the goods receipt and invoice settlement processes as representative use cases, where delivery notes and invoices must be matched and verified against purchase order SoR. Our results show that agentic approaches generally match or exceed non-agentic baselines, with simpler paradigms matching or outperforming complex alternatives. Paired with systematic error analysis, this work provides actionable guidance for deploying agentic document AI at enterprise scale.</abstract>
<identifier type="citekey">zhang-etal-2026-agents</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.200/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3357</start>
<end>3375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Agents Help? Agentic Document Information Extraction with Enterprise Database Grounding
%A Zhang, Zhijie
%A Shao, Hongxin
%A Geiger, Mattis Lennart
%A Bai, Tao
%A Dahlmeier, Daniel
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F zhang-etal-2026-agents
%X In enterprise applications, document information extraction (IE) does not operate in isolation: extracted information must match the systems of record (SoR) for the process to work. While reliable IE demands entity extraction, SoR grounding, and iterative refinement, existing methods rely on single-pass inference. To address this gap, we propose a SoR-grounded agentic pipeline and evaluate four agentic paradigms (Agentic Workflow, ReAct, Plan-Execute-Critic, and Dynamic Agent Collaboration) on real-world enterprise data. We focus on the goods receipt and invoice settlement processes as representative use cases, where delivery notes and invoices must be matched and verified against purchase order SoR. Our results show that agentic approaches generally match or exceed non-agentic baselines, with simpler paradigms matching or outperforming complex alternatives. Paired with systematic error analysis, this work provides actionable guidance for deploying agentic document AI at enterprise scale.
%U https://aclanthology.org/2026.emnlp-industry.200/
%P 3357-3375
Markdown (Informal)
[Do Agents Help? Agentic Document Information Extraction with Enterprise Database Grounding](https://aclanthology.org/2026.emnlp-industry.200/) (Zhang et al., EMNLP 2026)
ACL