@inproceedings{won-lee-2026-findra,
title = "{F}in{DRA}: Multi-Agent Financial Reasoning under Asymmetric Information and Unequal Authority",
author = "Won, Inyoung and
Lee, Yunyoung",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.18/",
pages = "224--236",
ISBN = "979-8-89176-466-8",
abstract = "We propose FinDRA, a multi-agent framework for financial question answering under asymmetric information access. FinDRA partitions a financial report into agent-specific evidence regions, allows agents to exchange only their answers, concise reasoning, and confidence estimates, and coordinates their revisions through full-document verifier feedback and authority-framed debate. Experiments on MultiHiertt show that the asymmetric verifier condition obtains the highest overall point estimates among the compared settings, with an EM score of 0.284 and a mean LLM-as-a-Judge score of 0.753 on a 0{--}2 scale. Importantly, the benefit of asymmetric access depends on evidence structure: it is strongest when question-relevant evidence remains within an agent-accessible region, whereas cross-partition questions expose a trade-off between semantic adequacy and exact numerical agreement. Agent-level analyses further show revision patterns consistent with the assigned authority framing, without attributing these differences to authority alone. Cross-dataset experiments on FinQA and TAT-QA similarly show that asymmetric access is not universally beneficial. These findings suggest that effective multi-agent financial reasoning depends not simply on providing more information, but on how evidence is partitioned, communicated, and verified."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="won-lee-2026-findra">
<titleInfo>
<title>FinDRA: Multi-Agent Financial Reasoning under Asymmetric Information and Unequal Authority</title>
</titleInfo>
<name type="personal">
<namePart type="given">Inyoung</namePart>
<namePart type="family">Won</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyoung</namePart>
<namePart type="family">Lee</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 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>We propose FinDRA, a multi-agent framework for financial question answering under asymmetric information access. FinDRA partitions a financial report into agent-specific evidence regions, allows agents to exchange only their answers, concise reasoning, and confidence estimates, and coordinates their revisions through full-document verifier feedback and authority-framed debate. Experiments on MultiHiertt show that the asymmetric verifier condition obtains the highest overall point estimates among the compared settings, with an EM score of 0.284 and a mean LLM-as-a-Judge score of 0.753 on a 0–2 scale. Importantly, the benefit of asymmetric access depends on evidence structure: it is strongest when question-relevant evidence remains within an agent-accessible region, whereas cross-partition questions expose a trade-off between semantic adequacy and exact numerical agreement. Agent-level analyses further show revision patterns consistent with the assigned authority framing, without attributing these differences to authority alone. Cross-dataset experiments on FinQA and TAT-QA similarly show that asymmetric access is not universally beneficial. These findings suggest that effective multi-agent financial reasoning depends not simply on providing more information, but on how evidence is partitioned, communicated, and verified.</abstract>
<identifier type="citekey">won-lee-2026-findra</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.18/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>224</start>
<end>236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FinDRA: Multi-Agent Financial Reasoning under Asymmetric Information and Unequal Authority
%A Won, Inyoung
%A Lee, Yunyoung
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F won-lee-2026-findra
%X We propose FinDRA, a multi-agent framework for financial question answering under asymmetric information access. FinDRA partitions a financial report into agent-specific evidence regions, allows agents to exchange only their answers, concise reasoning, and confidence estimates, and coordinates their revisions through full-document verifier feedback and authority-framed debate. Experiments on MultiHiertt show that the asymmetric verifier condition obtains the highest overall point estimates among the compared settings, with an EM score of 0.284 and a mean LLM-as-a-Judge score of 0.753 on a 0–2 scale. Importantly, the benefit of asymmetric access depends on evidence structure: it is strongest when question-relevant evidence remains within an agent-accessible region, whereas cross-partition questions expose a trade-off between semantic adequacy and exact numerical agreement. Agent-level analyses further show revision patterns consistent with the assigned authority framing, without attributing these differences to authority alone. Cross-dataset experiments on FinQA and TAT-QA similarly show that asymmetric access is not universally beneficial. These findings suggest that effective multi-agent financial reasoning depends not simply on providing more information, but on how evidence is partitioned, communicated, and verified.
%U https://aclanthology.org/2026.finnlp-1.18/
%P 224-236
Markdown (Informal)
[FinDRA: Multi-Agent Financial Reasoning under Asymmetric Information and Unequal Authority](https://aclanthology.org/2026.finnlp-1.18/) (Won & Lee, FinNLP 2026)
ACL