@inproceedings{liu-etal-2026-slit,
title = "{SLIT}: Execution-Grounded Small Language Models for Issue-Reproducing Test Generation",
author = "Liu, Runlin and
Zhang, Zhe and
Chen, Zeren and
Gao, Xiang and
Sheng, Lu and
Yang, Ping and
Li, Mu and
Sun, Hailong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.945/",
pages = "21776--21792",
ISBN = "979-8-89176-459-0",
abstract = "Automatically generating issue-reproducing tests is essential for debugging and regression prevention. Recent advances show that large language models can effectively perform this task, but their reliance on extremely large parameter scales limits practical deployment. In this paper, we propose SLIT, an execution-grounded framework that enables small language models to generate effective issue-reproducing tests. SLIT formulates issue reproduction as an execution-guided exploration problem and optimizes policies with reinforcement learning over execution-based rewards. To improve inference-time exploration, SLIT further introduces diversity-augmented test construction and a learned scoring model to select effective reproducing tests. Experimental results on SWT-Bench-Verified indicate that the 14B-parameter model achieves a resolve rate of 46.2{\%}, achieving competitive performance against prior approaches that rely on larger models. These results demonstrate the effectiveness of SLIT and highlight the viability of execution-grounded small language models for issue-reproducing test generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-slit">
<titleInfo>
<title>SLIT: Execution-Grounded Small Language Models for Issue-Reproducing Test Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Runlin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeren</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Sheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailong</namePart>
<namePart type="family">Sun</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</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Automatically generating issue-reproducing tests is essential for debugging and regression prevention. Recent advances show that large language models can effectively perform this task, but their reliance on extremely large parameter scales limits practical deployment. In this paper, we propose SLIT, an execution-grounded framework that enables small language models to generate effective issue-reproducing tests. SLIT formulates issue reproduction as an execution-guided exploration problem and optimizes policies with reinforcement learning over execution-based rewards. To improve inference-time exploration, SLIT further introduces diversity-augmented test construction and a learned scoring model to select effective reproducing tests. Experimental results on SWT-Bench-Verified indicate that the 14B-parameter model achieves a resolve rate of 46.2%, achieving competitive performance against prior approaches that rely on larger models. These results demonstrate the effectiveness of SLIT and highlight the viability of execution-grounded small language models for issue-reproducing test generation.</abstract>
<identifier type="citekey">liu-etal-2026-slit</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.945/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>21776</start>
<end>21792</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLIT: Execution-Grounded Small Language Models for Issue-Reproducing Test Generation
%A Liu, Runlin
%A Zhang, Zhe
%A Chen, Zeren
%A Gao, Xiang
%A Sheng, Lu
%A Yang, Ping
%A Li, Mu
%A Sun, Hailong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liu-etal-2026-slit
%X Automatically generating issue-reproducing tests is essential for debugging and regression prevention. Recent advances show that large language models can effectively perform this task, but their reliance on extremely large parameter scales limits practical deployment. In this paper, we propose SLIT, an execution-grounded framework that enables small language models to generate effective issue-reproducing tests. SLIT formulates issue reproduction as an execution-guided exploration problem and optimizes policies with reinforcement learning over execution-based rewards. To improve inference-time exploration, SLIT further introduces diversity-augmented test construction and a learned scoring model to select effective reproducing tests. Experimental results on SWT-Bench-Verified indicate that the 14B-parameter model achieves a resolve rate of 46.2%, achieving competitive performance against prior approaches that rely on larger models. These results demonstrate the effectiveness of SLIT and highlight the viability of execution-grounded small language models for issue-reproducing test generation.
%U https://aclanthology.org/2026.emnlp-main.945/
%P 21776-21792
Markdown (Informal)
[SLIT: Execution-Grounded Small Language Models for Issue-Reproducing Test Generation](https://aclanthology.org/2026.emnlp-main.945/) (Liu et al., EMNLP 2026)
ACL
- Runlin Liu, Zhe Zhang, Zeren Chen, Xiang Gao, Lu Sheng, Ping Yang, Mu Li, and Hailong Sun. 2026. SLIT: Execution-Grounded Small Language Models for Issue-Reproducing Test Generation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 21776–21792, Budapest, Hungary. Association for Computational Linguistics.