@inproceedings{wang-etal-2026-arkrepobench,
title = "{A}rk{R}epo{B}ench: A Repository-Level Code Completion Benchmark for {H}armony{OS} Development",
author = "Wang, Yanlin and
Zhang, Bowen and
Wang, Yanli and
Guo, Daya and
Zhuo, Terry Yue and
Chen, Jiachi and
Liu, Mingwei and
Zhang, Xingong and
Zheng, Zibin",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.969/",
pages = "19409--19429",
ISBN = "979-8-89176-395-1",
abstract = "ArkTS is the primary programming language for Huawei{'}s HarmonyOS ecosystem, which has expanded across smartphones, tablets, and IoT devices. While large language models have demonstrated strong code generation capabilities for mainstream languages, their performance on ArkTS remains largely unexplored. To address this gap, we introduce ArkRepoBench, the first repository-level code completion benchmark for ArkTS to our knowledge, 7,519 samples from 20 official HarmonyOS repositories. The benchmark covers multiple difficulty levels and further categorizes completion instances into Single-File, Cross-File Independent, and Cross-File Dependent settings based on dependency analysis, distinguishing the mere presence of cross-file context from its actual necessity. Our experiments show that: (1) ArkTS completion consistently underperforms mainstream languages under our experimental settings, suggesting language-specific challenges associated with this emerging language; (2) open-source 7B models achieve performance comparable to close-source models; (3) cross-file context is a double-edged sword, with sparse retrieval(Jaccard) outperforming dense methods on ArkTS; and (4) HarmonyOS API documentation consistently improves performance, suggesting the benefits of domain-specific enhancements in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-arkrepobench">
<titleInfo>
<title>ArkRepoBench: A Repository-Level Code Completion Benchmark for HarmonyOS Development</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanlin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanli</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daya</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="given">Yue</namePart>
<namePart type="family">Zhuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiachi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zibin</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>ArkTS is the primary programming language for Huawei’s HarmonyOS ecosystem, which has expanded across smartphones, tablets, and IoT devices. While large language models have demonstrated strong code generation capabilities for mainstream languages, their performance on ArkTS remains largely unexplored. To address this gap, we introduce ArkRepoBench, the first repository-level code completion benchmark for ArkTS to our knowledge, 7,519 samples from 20 official HarmonyOS repositories. The benchmark covers multiple difficulty levels and further categorizes completion instances into Single-File, Cross-File Independent, and Cross-File Dependent settings based on dependency analysis, distinguishing the mere presence of cross-file context from its actual necessity. Our experiments show that: (1) ArkTS completion consistently underperforms mainstream languages under our experimental settings, suggesting language-specific challenges associated with this emerging language; (2) open-source 7B models achieve performance comparable to close-source models; (3) cross-file context is a double-edged sword, with sparse retrieval(Jaccard) outperforming dense methods on ArkTS; and (4) HarmonyOS API documentation consistently improves performance, suggesting the benefits of domain-specific enhancements in low-resource settings.</abstract>
<identifier type="citekey">wang-etal-2026-arkrepobench</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.969/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>19409</start>
<end>19429</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArkRepoBench: A Repository-Level Code Completion Benchmark for HarmonyOS Development
%A Wang, Yanlin
%A Zhang, Bowen
%A Wang, Yanli
%A Guo, Daya
%A Zhuo, Terry Yue
%A Chen, Jiachi
%A Liu, Mingwei
%A Zhang, Xingong
%A Zheng, Zibin
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F wang-etal-2026-arkrepobench
%X ArkTS is the primary programming language for Huawei’s HarmonyOS ecosystem, which has expanded across smartphones, tablets, and IoT devices. While large language models have demonstrated strong code generation capabilities for mainstream languages, their performance on ArkTS remains largely unexplored. To address this gap, we introduce ArkRepoBench, the first repository-level code completion benchmark for ArkTS to our knowledge, 7,519 samples from 20 official HarmonyOS repositories. The benchmark covers multiple difficulty levels and further categorizes completion instances into Single-File, Cross-File Independent, and Cross-File Dependent settings based on dependency analysis, distinguishing the mere presence of cross-file context from its actual necessity. Our experiments show that: (1) ArkTS completion consistently underperforms mainstream languages under our experimental settings, suggesting language-specific challenges associated with this emerging language; (2) open-source 7B models achieve performance comparable to close-source models; (3) cross-file context is a double-edged sword, with sparse retrieval(Jaccard) outperforming dense methods on ArkTS; and (4) HarmonyOS API documentation consistently improves performance, suggesting the benefits of domain-specific enhancements in low-resource settings.
%U https://aclanthology.org/2026.findings-acl.969/
%P 19409-19429
Markdown (Informal)
[ArkRepoBench: A Repository-Level Code Completion Benchmark for HarmonyOS Development](https://aclanthology.org/2026.findings-acl.969/) (Wang et al., Findings 2026)
ACL
- Yanlin Wang, Bowen Zhang, Yanli Wang, Daya Guo, Terry Yue Zhuo, Jiachi Chen, Mingwei Liu, Xingong Zhang, and Zibin Zheng. 2026. ArkRepoBench: A Repository-Level Code Completion Benchmark for HarmonyOS Development. In Findings of the Association for Computational Linguistics: ACL 2026, pages 19409–19429, San Diego, California, United States. Association for Computational Linguistics.