EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG
This addresses the bottleneck of verification in embedded software development workflows, offering a domain-specific solution with incremental improvements through automation.
The paper tackled the problem of manual test development for embedded C software by proposing a Retrieval-Augmented Generation (RAG) pipeline, which achieved 100% syntactically correct tests, 85% runtime validation success, and potential time savings of up to 66% compared to manual methods.
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.