@inproceedings{zhang-etal-2026-cycleie,
title = "{C}ycle{IE}: Robust Document Information Extraction through Iterative Verification and Refinement",
author = "Zhang, Zhengxuan and
WU, Yin and
Liang, Zhuowen and
Wang, Haixun and
Luo, Yuyu and
Tang, Nan",
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.418/",
pages = "8813--8829",
ISBN = "979-8-89176-462-0",
abstract = "In document AI, reliable analytics require converting long, noisy (often multi-document) corpora into heterogeneous structured data{---}e.g., tables for numerical fields, graphs for relations, and trees for hierarchies. Yet, one-pass LLM extraction often yields incomplete or inconsistent structures because it lacks explicit verification and opportunities to revise earlier choices. We present CycleIE, an iterative information extraction (IE) framework that closes the loop between reasoning and acting by coupling ReAct with Monte Carlo Tree Search (MCTS). CycleIE employs a multi-agent workflow to iteratively retrieve, structure, extract, and refine content under verification guidance. By treating extraction as a feedback-driven search process, CycleIE systematically corrects omissions and inconsistencies that defeat one-pass methods, while remaining orthogonal to retrieval-augmented generation (RAG). Experiments on challenging document-based QA benchmarks demonstrate that CycleIE delivers {\ensuremath{>}}10{\%} relative improvements over strong baselines, particularly in lengthy or multi-document contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-cycleie">
<titleInfo>
<title>CycleIE: Robust Document Information Extraction through Iterative Verification and Refinement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="family">WU</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuowen</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haixun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyu</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Tang</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>In document AI, reliable analytics require converting long, noisy (often multi-document) corpora into heterogeneous structured data—e.g., tables for numerical fields, graphs for relations, and trees for hierarchies. Yet, one-pass LLM extraction often yields incomplete or inconsistent structures because it lacks explicit verification and opportunities to revise earlier choices. We present CycleIE, an iterative information extraction (IE) framework that closes the loop between reasoning and acting by coupling ReAct with Monte Carlo Tree Search (MCTS). CycleIE employs a multi-agent workflow to iteratively retrieve, structure, extract, and refine content under verification guidance. By treating extraction as a feedback-driven search process, CycleIE systematically corrects omissions and inconsistencies that defeat one-pass methods, while remaining orthogonal to retrieval-augmented generation (RAG). Experiments on challenging document-based QA benchmarks demonstrate that CycleIE delivers \ensuremath>10% relative improvements over strong baselines, particularly in lengthy or multi-document contexts.</abstract>
<identifier type="citekey">zhang-etal-2026-cycleie</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.418/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8813</start>
<end>8829</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CycleIE: Robust Document Information Extraction through Iterative Verification and Refinement
%A Zhang, Zhengxuan
%A WU, Yin
%A Liang, Zhuowen
%A Wang, Haixun
%A Luo, Yuyu
%A Tang, Nan
%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 zhang-etal-2026-cycleie
%X In document AI, reliable analytics require converting long, noisy (often multi-document) corpora into heterogeneous structured data—e.g., tables for numerical fields, graphs for relations, and trees for hierarchies. Yet, one-pass LLM extraction often yields incomplete or inconsistent structures because it lacks explicit verification and opportunities to revise earlier choices. We present CycleIE, an iterative information extraction (IE) framework that closes the loop between reasoning and acting by coupling ReAct with Monte Carlo Tree Search (MCTS). CycleIE employs a multi-agent workflow to iteratively retrieve, structure, extract, and refine content under verification guidance. By treating extraction as a feedback-driven search process, CycleIE systematically corrects omissions and inconsistencies that defeat one-pass methods, while remaining orthogonal to retrieval-augmented generation (RAG). Experiments on challenging document-based QA benchmarks demonstrate that CycleIE delivers \ensuremath>10% relative improvements over strong baselines, particularly in lengthy or multi-document contexts.
%U https://aclanthology.org/2026.findings-emnlp.418/
%P 8813-8829
Markdown (Informal)
[CycleIE: Robust Document Information Extraction through Iterative Verification and Refinement](https://aclanthology.org/2026.findings-emnlp.418/) (Zhang et al., Findings 2026)
ACL