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

2026-03-10

AI Summary

This study addresses the inefficiency of manual test development for embedded C software, which has become a critical verification bottleneck in rapid iteration cycles. To overcome this challenge, the work proposes the first automated test generation approach that integrates Retrieval-Augmented Generation (RAG) with large language models (LLMs), leveraging project-specific code and documentation as contextual input. This strategy significantly mitigates model hallucination and enhances the contextual consistency of generated test cases. Experimental results demonstrate that the generated tests achieve 100% syntactic correctness, with 85% passing runtime validation. The method produces tests at a rate of 270 per hour, reducing development time by up to 66% compared to manual authoring.

Technology Category

Natural Language Processing: Code Generation / Program Synthesis from Natural LanguageMachine Learning: Large Multimodal Models (LMMs)Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving

Application Category

Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAGEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• embedded software testing
• test automation
• verification bottleneck
• manual test development
• software release cycles

Innovation

• Retrieval-Augmented Generation
• Large Language Models
• Embedded Software Testing
• Test Automation
• Hallucination Reduction