<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2026-medcalc">
    <titleInfo>
        <title>MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Siran</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruihui</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyue</namePart>
        <namePart type="family">Huai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chennuo</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tong</namePart>
        <namePart type="family">Ruan</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>Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query. However, real clinical scenarios often require multiple calculators for joint evaluation, nested-calculator calculation, and fuzzy queries that do not directly specify the target calculator. To this end, we propose a new medical calculation benchmark, MedCalc-Pro, which covers three progressively challenging task settings: single-calculator, multi-calculator, and nested-calculator calculation settings. MedCalc-Pro contains 2,268 real-world clinical cases, covering 77 medical calculators across 14 clinical departments. Meanwhile, to address the limited performance of existing frameworks and methods in complex clinical scenarios, we further propose a more generalizable agent framework that supports multi-calculator selection and nested-calculator calling, while suppressing parameter error propagation through structured validation and evidence audit. We conduct systematic comparisons across open-source, closed-source, and medical-specialized LLMs, and the results show that our framework achieves the best performance across all three task settings. This work provides a new benchmark and method for evaluating and applying LLMs in challenging medical calculation scenarios. The dataset and code are publicly available at https://github.com/easymoney7774/MedCalc-Pro.</abstract>
    <identifier type="citekey">zhao-etal-2026-medcalc</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1512</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1512/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>32187</start>
            <end>32208</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents
%A Zhao, Siran
%A Hou, Ruihui
%A Huai, Ziyue
%A Zhang, Chennuo
%A Ruan, Tong
%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 zhao-etal-2026-medcalc
%X Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query. However, real clinical scenarios often require multiple calculators for joint evaluation, nested-calculator calculation, and fuzzy queries that do not directly specify the target calculator. To this end, we propose a new medical calculation benchmark, MedCalc-Pro, which covers three progressively challenging task settings: single-calculator, multi-calculator, and nested-calculator calculation settings. MedCalc-Pro contains 2,268 real-world clinical cases, covering 77 medical calculators across 14 clinical departments. Meanwhile, to address the limited performance of existing frameworks and methods in complex clinical scenarios, we further propose a more generalizable agent framework that supports multi-calculator selection and nested-calculator calling, while suppressing parameter error propagation through structured validation and evidence audit. We conduct systematic comparisons across open-source, closed-source, and medical-specialized LLMs, and the results show that our framework achieves the best performance across all three task settings. This work provides a new benchmark and method for evaluating and applying LLMs in challenging medical calculation scenarios. The dataset and code are publicly available at https://github.com/easymoney7774/MedCalc-Pro.
%R 10.18653/2026.findings-emnlp.1512
%U https://aclanthology.org/2026.findings-emnlp.1512/
%U https://doi.org/10.18653/2026.findings-emnlp.1512
%P 32187-32208

Markdown (Informal)

[MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents](https://aclanthology.org/2026.findings-emnlp.1512/) (Zhao et al., Findings 2026)

• MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents (Zhao et al., Findings 2026)

ACL

• Siran Zhao, Ruihui Hou, Ziyue Huai, Chennuo Zhang, and Tong Ruan. 2026. MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 32187–32208, Budapest, Hungary. Association for Computational Linguistics.