Research

Paper

AI LLM March 10, 2026

EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG

Authors

Maximilian Harnot, Sebastian Komarnicki, Michal Polok, Timo Oksanen

Abstract

Manual development of automatic tests for embedded C software is a strenuous and time-consuming task that does not scale well. With the accelerating pace of software release cycles, verification increasingly becomes the bottleneck in the embedded development workflow. This paper presents a Retrieval-Augmented Generation (RAG) pipeline as a solution for partial automation of the verification process. By grounding a large language model in project-specific artifacts, the approach reduces hallucinations and improves project alignment. An industrial evaluation showed that the generated tests are 100 % syntactically correct, with 85 % successfully passing runtime validation. The proposed solution has the potential to save up to 66 % of the testing time compared to manual test writing while generating 270 tests per hour.

Metadata

arXiv ID: 2603.09497
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09497v1</id>\n    <title>EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG</title>\n    <updated>2026-03-10T10:58:59Z</updated>\n    <link href='https://arxiv.org/abs/2603.09497v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09497v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Manual development of automatic tests for embedded C software is a strenuous and time-consuming task that does not scale well. With the accelerating pace of software release cycles, verification increasingly becomes the bottleneck in the embedded development workflow. This paper presents a Retrieval-Augmented Generation (RAG) pipeline as a solution for partial automation of the verification process. By grounding a large language model in project-specific artifacts, the approach reduces hallucinations and improves project alignment. An industrial evaluation showed that the generated tests are 100 % syntactically correct, with 85 % successfully passing runtime validation. The proposed solution has the potential to save up to 66 % of the testing time compared to manual test writing while generating 270 tests per hour.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <published>2026-03-10T10:58:59Z</published>\n    <arxiv:primary_category term='cs.SE'/>\n    <arxiv:journal_ref>Technical University of Munich. 2026. ISBN 978-3-911430-12-8. https://mediatum.ub.tum.de/1846559</arxiv:journal_ref>\n    <author>\n      <name>Maximilian Harnot</name>\n    </author>\n    <author>\n      <name>Sebastian Komarnicki</name>\n    </author>\n    <author>\n      <name>Michal Polok</name>\n    </author>\n    <author>\n      <name>Timo Oksanen</name>\n    </author>\n  </entry>"
}