@inproceedings{nacar-etal-2026-aisa,
title = "{AISA}-{A}rabic{FC}: The First Shared Task on {A}rabic Function Calling for Agentic {AI} Systems",
author = "Nacar, Omer and
Alzubaidi, Wareef and
Alkhalifah, Mohammed",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.198/",
pages = "1531--1546",
ISBN = "979-8-89176-497-2",
abstract = "Function calling connects language models to external tools, but Arabic structured tool use remains insufficiently evaluated. We present , a shared task at ArabicNLP{~}2026 built around $12{,}220$ Arabic requests spanning five dialect groups and eight service domains. Each request has four candidate schemas drawn from a registry of 27 tools, including seven tools that never occur as gold calls; 223 requests require abstention. Systems decide whether to call, select a function, and extract its arguments. Two ranked tracks evaluate core calling and reasoning-trace compliance, with a third diagnostic examining dialect robustness. Twenty-two teams submitted to the blind phase, and 21 produced valid predictions on $1{,}125$ test requests. We analyze 73 submissions and 13 system descriptions. A LoRA-adapted 4B model ranks first on both competition tracks, with scores of 0.9279 and 0.9400, while argument exact match peaks at 0.8816. However, a deterministic rule combining candidate order and released metadata matches the best observed function-name accuracy of 0.9973, limiting what this metric establishes about language understanding. Exact argument extraction provides most of the competitive separation. Maghrebi has the lowest score for every system, although its small test subset and differences in example composition limit interpretation. We provide public task data, a baseline checkpoint, the scorer, and final rankings, and document evaluation shortcuts and remaining reproducibility limitations.[{\ensuremath{<}}https://huggingface.co/spaces/TuwaiqAcademy/AISA-ArabicFC-Shared-Task{\ensuremath{>}}]"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nacar-etal-2026-aisa">
<titleInfo>
<title>AISA-ArabicFC: The First Shared Task on Arabic Function Calling for Agentic AI Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wareef</namePart>
<namePart type="family">Alzubaidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Alkhalifah</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 Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</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">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>Function calling connects language models to external tools, but Arabic structured tool use remains insufficiently evaluated. We present , a shared task at ArabicNLP 2026 built around 12,220 Arabic requests spanning five dialect groups and eight service domains. Each request has four candidate schemas drawn from a registry of 27 tools, including seven tools that never occur as gold calls; 223 requests require abstention. Systems decide whether to call, select a function, and extract its arguments. Two ranked tracks evaluate core calling and reasoning-trace compliance, with a third diagnostic examining dialect robustness. Twenty-two teams submitted to the blind phase, and 21 produced valid predictions on 1,125 test requests. We analyze 73 submissions and 13 system descriptions. A LoRA-adapted 4B model ranks first on both competition tracks, with scores of 0.9279 and 0.9400, while argument exact match peaks at 0.8816. However, a deterministic rule combining candidate order and released metadata matches the best observed function-name accuracy of 0.9973, limiting what this metric establishes about language understanding. Exact argument extraction provides most of the competitive separation. Maghrebi has the lowest score for every system, although its small test subset and differences in example composition limit interpretation. We provide public task data, a baseline checkpoint, the scorer, and final rankings, and document evaluation shortcuts and remaining reproducibility limitations.[\ensuremath<https://huggingface.co/spaces/TuwaiqAcademy/AISA-ArabicFC-Shared-Task\ensuremath>]</abstract>
<identifier type="citekey">nacar-etal-2026-aisa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.198/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1531</start>
<end>1546</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AISA-ArabicFC: The First Shared Task on Arabic Function Calling for Agentic AI Systems
%A Nacar, Omer
%A Alzubaidi, Wareef
%A Alkhalifah, Mohammed
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F nacar-etal-2026-aisa
%X Function calling connects language models to external tools, but Arabic structured tool use remains insufficiently evaluated. We present , a shared task at ArabicNLP 2026 built around 12,220 Arabic requests spanning five dialect groups and eight service domains. Each request has four candidate schemas drawn from a registry of 27 tools, including seven tools that never occur as gold calls; 223 requests require abstention. Systems decide whether to call, select a function, and extract its arguments. Two ranked tracks evaluate core calling and reasoning-trace compliance, with a third diagnostic examining dialect robustness. Twenty-two teams submitted to the blind phase, and 21 produced valid predictions on 1,125 test requests. We analyze 73 submissions and 13 system descriptions. A LoRA-adapted 4B model ranks first on both competition tracks, with scores of 0.9279 and 0.9400, while argument exact match peaks at 0.8816. However, a deterministic rule combining candidate order and released metadata matches the best observed function-name accuracy of 0.9973, limiting what this metric establishes about language understanding. Exact argument extraction provides most of the competitive separation. Maghrebi has the lowest score for every system, although its small test subset and differences in example composition limit interpretation. We provide public task data, a baseline checkpoint, the scorer, and final rankings, and document evaluation shortcuts and remaining reproducibility limitations.[\ensuremath<https://huggingface.co/spaces/TuwaiqAcademy/AISA-ArabicFC-Shared-Task\ensuremath>]
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.198/
%P 1531-1546
Markdown (Informal)
[AISA-ArabicFC: The First Shared Task on Arabic Function Calling for Agentic AI Systems](https://aclanthology.org/2026.arabicnlp-sharedtasks.198/) (Nacar et al., ArabicNLP 2026)
ACL