@inproceedings{soni-etal-2026-swe,
title = "{SWE}-Tester: Training Open-Source {LLM}s for Issue Reproduction in Real-World Repositories",
author = "Soni, Aditya Bharat and
Ghosh, Rajat and
Bhargava, Vaishnavi and
Chen, Valerie and
Dutta, Debojyoti",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.43/",
pages = "720--729",
ISBN = "979-8-89176-460-6",
abstract = "Software testing is essential for maintaining software reliability, yet issue reproduction tests are often missing when bugs are reported. Automatically generating such tests can accelerate debugging, support test-driven development, and improve automated software engineering systems that rely on execution-based verification. Existing approaches largely depend on proprietary language models, limiting accessibility and reproducibility. We present SWE-Tester a framework for training open-source large language models to generate issue reproduction tests from natural language issue reports. To support this task, we curate a dataset of 41K training instances from 2.6K open-source GitHub repositories. Fine-tuning on this dataset improves issue reproduction performance across multiple model families, yielding gains of up to 10{\%} points in success rate and 21{\%} in change coverage on SWT-Bench Verified. We further study the effects of model size, training data scale, and inference-time compute, observing consistent improvements along all three axes. Our results demonstrate that open-source models can be effectively specialized for issue reproduction test generation and provide a scalable foundation for future software testing and automated issue-resolution systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soni-etal-2026-swe">
<titleInfo>
<title>SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="given">Bharat</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajat</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaishnavi</namePart>
<namePart type="family">Bhargava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debojyoti</namePart>
<namePart type="family">Dutta</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>Software testing is essential for maintaining software reliability, yet issue reproduction tests are often missing when bugs are reported. Automatically generating such tests can accelerate debugging, support test-driven development, and improve automated software engineering systems that rely on execution-based verification. Existing approaches largely depend on proprietary language models, limiting accessibility and reproducibility. We present SWE-Tester a framework for training open-source large language models to generate issue reproduction tests from natural language issue reports. To support this task, we curate a dataset of 41K training instances from 2.6K open-source GitHub repositories. Fine-tuning on this dataset improves issue reproduction performance across multiple model families, yielding gains of up to 10% points in success rate and 21% in change coverage on SWT-Bench Verified. We further study the effects of model size, training data scale, and inference-time compute, observing consistent improvements along all three axes. Our results demonstrate that open-source models can be effectively specialized for issue reproduction test generation and provide a scalable foundation for future software testing and automated issue-resolution systems.</abstract>
<identifier type="citekey">soni-etal-2026-swe</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.43/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>720</start>
<end>729</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories
%A Soni, Aditya Bharat
%A Ghosh, Rajat
%A Bhargava, Vaishnavi
%A Chen, Valerie
%A Dutta, Debojyoti
%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 soni-etal-2026-swe
%X Software testing is essential for maintaining software reliability, yet issue reproduction tests are often missing when bugs are reported. Automatically generating such tests can accelerate debugging, support test-driven development, and improve automated software engineering systems that rely on execution-based verification. Existing approaches largely depend on proprietary language models, limiting accessibility and reproducibility. We present SWE-Tester a framework for training open-source large language models to generate issue reproduction tests from natural language issue reports. To support this task, we curate a dataset of 41K training instances from 2.6K open-source GitHub repositories. Fine-tuning on this dataset improves issue reproduction performance across multiple model families, yielding gains of up to 10% points in success rate and 21% in change coverage on SWT-Bench Verified. We further study the effects of model size, training data scale, and inference-time compute, observing consistent improvements along all three axes. Our results demonstrate that open-source models can be effectively specialized for issue reproduction test generation and provide a scalable foundation for future software testing and automated issue-resolution systems.
%U https://aclanthology.org/2026.emnlp-industry.43/
%P 720-729
Markdown (Informal)
[SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories](https://aclanthology.org/2026.emnlp-industry.43/) (Soni et al., EMNLP 2026)
ACL