{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:27:08Z","timestamp":1769725628533,"version":"3.49.0"},"reference-count":21,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106094"],"award-info":[{"award-number":["62106094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Jiangxi Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["20242BAB20071"],"award-info":[{"award-number":["20242BAB20071"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Nanchang University Innovation Fund Project","award":["XX202506040053"],"award-info":[{"award-number":["XX202506040053"]}]},{"name":"Talent Support Project","award":["2024D01234567"],"award-info":[{"award-number":["2024D01234567"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>This paper introduces LLM4ATS, a framework integrating large language models, RAG, and closed-loop verification to automatically generate highly reliable automotive automated test scripts from natural language descriptions. Addressing the complex linguistic structure, strict rules, and strong dependency on the in-vehicle communication database inherent in ATS scripts, LLM4ATS innovatively employs fine-grained line-level generation and a rule-guided iterative refinement mechanism. The framework first enhances prompt context by retrieving relevant information from constructed syntax and case knowledge bases via RAG. Subsequently, each generated script line undergoes rigorous verification through a two-stage validator: initial syntax validation followed by semantic compliance checks against the communication database for signal paths and value domains. Any errors trigger structured feedback, driving iterative refinement by the large language model until fully compliant scripts are produced. This paper evaluated the framework\u2019s effectiveness on real ATS datasets, testing models including GPT-3.5, GPT-4, Qwen2.5-7B, and Qwen2.5-72B-Instruct. Experimental results demonstrate that compared to zero-shot and few-shot baseline methods, the LLM4ATS framework significantly improves generation quality and pass rates across all models. Notably, the strongest GPT-4 model achieved a script pass rate of 91% with LLM4ATS, up from 42% in zero-shot mode, and validated functional effectiveness on a specified in-vehicle hardware platform (Chery Fengyun T28 dashboard). At the same time, expert manual evaluations confirmed the superior performance of the generated scripts in correctness, readability, and compliance with industry standards.<\/jats:p>","DOI":"10.3390\/bdcc10020041","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:56:12Z","timestamp":1769615772000},"page":"41","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM4ATS: Applying Large Language Models for Auto-Testing Scripts in Automobiles"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7513-7235","authenticated-orcid":false,"given":"Zeyuan","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Engineering, Nanchang University, Nanchang 330031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4530-9816","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang University, Nanchang 330031, China"},{"name":"School of Artificial Intelligence, Nanchang University, Nanchang 330031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuezhao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang University, Nanchang 330031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang University, Nanchang 330031, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0960-4447","authenticated-orcid":false,"given":"Min","family":"Chen","sequence":"additional","affiliation":[{"name":"Pazhou Laboratory, Guangzhou 510640, China"},{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou 510641, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"ref_1","unstructured":"(2025, December 10). Smart Cars Market Trend. Available online: https:\/\/www.gminsights.com\/zh\/industry-analysis\/smart-motor-market."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Navet, N., and Simonot-Lion, F. (2017). Automotive Embedded Systems Handbook, CRC Press.","DOI":"10.1201\/9780849380273"},{"key":"ref_3","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_4","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_5","unstructured":"Radford, A., Wu, J., Amodei, D., Clark, J., Brundage, M., and Sutskever, I. (2019, February 14). Better Language Models and Their Implications. OpenAI Blog, Available online: https:\/\/openai.com\/index\/better-language-models\/."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Deng, Y., Liu, Q., Li, X., Zhang, G., and Zhu, M. (2024). A Survey of Mixture Models for Scientific Literature. Proceedings of the 2024 4th International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM), Chengdu, China, 20\u201322 December 2024, IEEE.","DOI":"10.1109\/AIIM64537.2024.10934484"},{"key":"ref_7","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V., Zhou, D., Zhou, Y., and Xie, Y. (December, January 28). Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Proceedings of the Advances in Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_8","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., and Hajishirzi, H. (2024, January 7\u201311). Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria."},{"key":"ref_9","unstructured":"Chan, C.M., Xu, C., Yuan, R., Luo, H., Xue, W., Guo, Y., and Fu, J. (2024, January 7\u20139). RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation. Proceedings of the First Conference on Language Modeling, Philadelphia, PA, USA."},{"key":"ref_10","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.T., and Rockt\u00e4schel, T. (2020, January 6\u201312). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Proceedings of the Advances in Neural Information Processing Systems, Virtual."},{"key":"ref_11","unstructured":"Han, Z., Gao, C., Liu, J., Zhang, J., and Zhang, S.Q. (2024). Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey. arXiv."},{"key":"ref_12","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Fakih, M., Dharmaji, R., Moghaddas, Y., Quiros, G., Ogundare, O., and Faruque, M.A.A. (2024, January 14\u201320). LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems. Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice, Lisbon, Portugal.","DOI":"10.1145\/3639477.3639743"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Fakih, M., Dharmaji, R., Bouzidi, H., Araya, G.Q., Ogundare, O., and Faruque, M.A.A. (2025). LLM4CVE: Enabling Iterative Automated Vulnerability Repair with Large Language Models. arXiv.","DOI":"10.1109\/DSD67783.2025.00087"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1109\/ACCESS.2024.3517419","article-title":"Comprehensive Bibliographic Survey and Forward-Looking Recommendations for Software Defect Prediction: Datasets, Validation Methodologies, Prediction Approaches, and Tools","volume":"13","author":"Mustaqeem","year":"2025","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tsunoda, M., Monden, A., Toda, K., Tahir, A., Bennin, K.E., Nakasai, K., Nagura, M., and Matsumoto, K. (2022, January 23\u201324). Using Bandit Algorithms for Selecting Feature Reduction Techniques in Software Defect Prediction. Proceedings of the 2022 IEEE\/ACM 19th International Conference on Mining Software Repositories (MSR), Pittsburgh, PA, USA.","DOI":"10.1145\/3524842.3529093"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"129695","DOI":"10.1016\/j.neucom.2025.129695","article-title":"Two-tier deep and machine learning approach optimized by adaptive multi-population firefly algorithm for software defects prediction","volume":"630","author":"Villoth","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Kamei, Y., and Shihab, E. (2016, January 14\u201318). Defect Prediction: Accomplishments and Future Challenges. Proceedings of the 2016 IEEE 23rd International Conference on Software Analysis, Evolution, and Reengineering (SANER), Osaka, Japan.","DOI":"10.1109\/SANER.2016.56"},{"key":"ref_19","first-page":"2","article-title":"Automotive Electronics System, Software, and Local Area Network","volume":"Volume 1","author":"Kawamura","year":"2006","journal-title":"Proceedings of the Hardware\/Software Codesign and System Synthesis, International Conference"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sahoo, P., Singh, A.K., Saha, S., Jain, V., Mondal, S., and Chadha, A. (2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv.","DOI":"10.1007\/979-8-8688-0569-1_4"},{"key":"ref_21","first-page":"493","article-title":"Survey of Intelligent and Connected Vehicle Technologies: Architectures, Functions and Applications","volume":"62","author":"Cui","year":"2022","journal-title":"J. Tsinghua Univ. (Sci. Technol.)"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/2\/41\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T10:34:58Z","timestamp":1769682898000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/2\/41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":21,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["bdcc10020041"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10020041","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]}}}