<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2026-deploying">
    <titleInfo>
        <title>Deploying Programmatic Tool Calling for Large-Scale Agentic Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nhan</namePart>
        <namePart type="family">Nguyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hadi</namePart>
        <namePart type="family">Habibzadeh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ahmad</namePart>
        <namePart type="given">Magdy</namePart>
        <namePart type="family">Eid</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>Production tool calling for agentic systems must satisfy four operational requirements: bounded per-invocation cost, predictable latency, adaptability to evolving tool catalogs, and the ability to catch errors before execution. The ReAct paradigm keeps the large language model (LLM) in the loop, but at production scale, re-processing intermediate results inflates cost and latency and degrades answer quality. Programmatic tool calling (PTC) offers an alternative; the LLM generates a single script that resolves dependencies and extracts relevant fields in one inference pass. PTC is a harder generation task, however, because the LLM must produce code that handles complex, variable responses without observing intermediate results, and existing remedies each fail at least one of the four requirements. We describe a production deployment of PTC serving 26,528 invocations, paired with a three-layer abstract syntax tree (AST)-based validator that rejects invalid scripts before execution and requires no training data, preserving adaptability to evolving tool catalogs. This reduced average input tokens by 77%, latency by 21%, and increased the answered-query rate by 5.6 percentage points across 19 production agents.</abstract>
    <identifier type="citekey">nguyen-etal-2026-deploying</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.78/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1315</start>
            <end>1322</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Deploying Programmatic Tool Calling for Large-Scale Agentic Systems
%A Nguyen, Nhan
%A Habibzadeh, Hadi
%A Eid, Ahmad Magdy
%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 nguyen-etal-2026-deploying
%X Production tool calling for agentic systems must satisfy four operational requirements: bounded per-invocation cost, predictable latency, adaptability to evolving tool catalogs, and the ability to catch errors before execution. The ReAct paradigm keeps the large language model (LLM) in the loop, but at production scale, re-processing intermediate results inflates cost and latency and degrades answer quality. Programmatic tool calling (PTC) offers an alternative; the LLM generates a single script that resolves dependencies and extracts relevant fields in one inference pass. PTC is a harder generation task, however, because the LLM must produce code that handles complex, variable responses without observing intermediate results, and existing remedies each fail at least one of the four requirements. We describe a production deployment of PTC serving 26,528 invocations, paired with a three-layer abstract syntax tree (AST)-based validator that rejects invalid scripts before execution and requires no training data, preserving adaptability to evolving tool catalogs. This reduced average input tokens by 77%, latency by 21%, and increased the answered-query rate by 5.6 percentage points across 19 production agents.
%U https://aclanthology.org/2026.emnlp-industry.78/
%P 1315-1322

Markdown (Informal)

[Deploying Programmatic Tool Calling for Large-Scale Agentic Systems](https://aclanthology.org/2026.emnlp-industry.78/) (Nguyen et al., EMNLP 2026)

• Deploying Programmatic Tool Calling for Large-Scale Agentic Systems (Nguyen et al., EMNLP 2026)

ACL

• Nhan Nguyen, Hadi Habibzadeh, and Ahmad Magdy Eid. 2026. Deploying Programmatic Tool Calling for Large-Scale Agentic Systems. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1315–1322, Budapest, Hungary. Association for Computational Linguistics.