Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915812058595328 |
|---|---|
| author | Cheng, Chih-Hong Liao, Brian Hsuan-Cheng Molin, Adam Esen, Hasan |
| author_facet | Cheng, Chih-Hong Liao, Brian Hsuan-Cheng Molin, Adam Esen, Hasan |
| contents | The adoption of large language models in safety-critical system engineering is constrained by trustworthiness, traceability, and alignment with established verification practices. We propose workflow-level design principles for trustworthy GenAI integration and demonstrate them in an end-to-end automotive pipeline, from requirement delta identification to SysML v2 architecture update and re-testing. First, we show that monolithic ("big-bang") prompting misses critical changes in large specifications, while section-wise decomposition with diversity sampling and lightweight NLP sanity checks improves completeness and correctness. Then, we propagate requirement deltas into SysML v2 models and validate updates via compilation and static analysis. Additionally, we ensure traceable regression testing by generating test cases through explicit mappings from specification variables to architectural ports and states, providing practical safeguards for GenAI used in safety-critical automotive engineering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19614 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering Cheng, Chih-Hong Liao, Brian Hsuan-Cheng Molin, Adam Esen, Hasan Software Engineering Machine Learning The adoption of large language models in safety-critical system engineering is constrained by trustworthiness, traceability, and alignment with established verification practices. We propose workflow-level design principles for trustworthy GenAI integration and demonstrate them in an end-to-end automotive pipeline, from requirement delta identification to SysML v2 architecture update and re-testing. First, we show that monolithic ("big-bang") prompting misses critical changes in large specifications, while section-wise decomposition with diversity sampling and lightweight NLP sanity checks improves completeness and correctness. Then, we propagate requirement deltas into SysML v2 models and validate updates via compilation and static analysis. Additionally, we ensure traceable regression testing by generating test cases through explicit mappings from specification variables to architectural ports and states, providing practical safeguards for GenAI used in safety-critical automotive engineering. |
| title | Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering |
| topic | Software Engineering Machine Learning |
| url | https://arxiv.org/abs/2602.19614 |