<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-raedt-etal-2026-coral">
    <titleInfo>
        <title>CORAL: Closed-loop Oracle Alignment for Agentic Tax Engine Modernization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maarten</namePart>
        <namePart type="family">De Raedt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="family">Abdullah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abhinav</namePart>
        <namePart type="family">Agrawal</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>Modernizing legacy software is often framed as code migration, an approach that assumes access to source code and an understanding of system internals. In practice these assumptions fail: source may be inaccessible, data in proprietary formats, and documentation dispersed. We study an underexplored regime in which a replacement is aligned to a legacy system treated as a black-box oracle, using only its input–output behavior.\par We present CORAL (Closed-loop Oracle Alignment), an agentic framework that aligns a modern U.S. individual income tax engine (Form 1040) to a production oracle (a system built over decades) by iteratively refining LLM-bootstrapped form schemas. Each round runs a scenario on both systems, compares e-file output field-by-field, and diagnoses discrepancies against an authoritative IRS knowledge base (KB), grounding every fix in published regulation rather than relying on model knowledge. An edit is kept only if re-execution shows no meaningful field-level F₁ regression and all tests pass, a deterministic check rather than model self-assessment. Round-robin sequencing over under-covered forms then reaches the long tail of forms, not just the high-frequency ones a taxpayer shares with everyone.\par Across 119 tax-expert-authored scenarios, each a complete taxpayer return, CORAL repairs defects from single-field corrections to reviving entire non-functional forms (53 fixed; 13 escalated to human review, ensuring ambiguous rules and input-data gaps are audited manually), lifting macro-F₁ on a 30-scenario held-out test split, averaged over returns, from an LLM-bootstrapped start (0.17) to 0.90.</abstract>
    <identifier type="citekey">de-raedt-etal-2026-coral</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.15/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>180</start>
            <end>192</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CORAL: Closed-loop Oracle Alignment for Agentic Tax Engine Modernization
%A De Raedt, Maarten
%A Abdullah, Ahmed
%A Agrawal, Abhinav
%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 de-raedt-etal-2026-coral
%X Modernizing legacy software is often framed as code migration, an approach that assumes access to source code and an understanding of system internals. In practice these assumptions fail: source may be inaccessible, data in proprietary formats, and documentation dispersed. We study an underexplored regime in which a replacement is aligned to a legacy system treated as a black-box oracle, using only its input–output behavior.\par We present CORAL (Closed-loop Oracle Alignment), an agentic framework that aligns a modern U.S. individual income tax engine (Form 1040) to a production oracle (a system built over decades) by iteratively refining LLM-bootstrapped form schemas. Each round runs a scenario on both systems, compares e-file output field-by-field, and diagnoses discrepancies against an authoritative IRS knowledge base (KB), grounding every fix in published regulation rather than relying on model knowledge. An edit is kept only if re-execution shows no meaningful field-level F₁ regression and all tests pass, a deterministic check rather than model self-assessment. Round-robin sequencing over under-covered forms then reaches the long tail of forms, not just the high-frequency ones a taxpayer shares with everyone.\par Across 119 tax-expert-authored scenarios, each a complete taxpayer return, CORAL repairs defects from single-field corrections to reviving entire non-functional forms (53 fixed; 13 escalated to human review, ensuring ambiguous rules and input-data gaps are audited manually), lifting macro-F₁ on a 30-scenario held-out test split, averaged over returns, from an LLM-bootstrapped start (0.17) to 0.90.
%U https://aclanthology.org/2026.finnlp-1.15/
%P 180-192

Markdown (Informal)

[CORAL: Closed-loop Oracle Alignment for Agentic Tax Engine Modernization](https://aclanthology.org/2026.finnlp-1.15/) (De Raedt et al., FinNLP 2026)

• CORAL: Closed-loop Oracle Alignment for Agentic Tax Engine Modernization (De Raedt et al., FinNLP 2026)

ACL

• Maarten De Raedt, Ahmed Abdullah, and Abhinav Agrawal. 2026. CORAL: Closed-loop Oracle Alignment for Agentic Tax Engine Modernization. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 180–192, Budapest, Hungary. Association for Computational Linguistics.