Saved in:
Bibliographic Details
Main Authors: Harnot, Maximilian, Komarnicki, Sebastian, Polok, Michal, Oksanen, Timo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915850456399872
author Harnot, Maximilian
Komarnicki, Sebastian
Polok, Michal
Oksanen, Timo
author_facet Harnot, Maximilian
Komarnicki, Sebastian
Polok, Michal
Oksanen, Timo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09497
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG
Harnot, Maximilian
Komarnicki, Sebastian
Polok, Michal
Oksanen, Timo
Software Engineering
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.
title EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG
topic Software Engineering
url https://arxiv.org/abs/2603.09497