ArticleOpen Access http://dx.doi.org/10.26855/acc.2025.10.017
Analysis of Implementation Pathways for Generative AI in Cross-language Code Migration and Compatibility Testing
Zhenlin Jin
Computer Science Department, University of Arkansas at Little Rock, Little Rock, AR 72204, USA.
*Corresponding author: Zhenlin Jin
Published: November 05, 2025
Abstract
Cross-language code migration and compatibility testing are critical processes in modern software engineering to enhance system maintainability and scalability. Generative artificial intelligence demonstrates unique advantages in code comprehension, semantic analysis, and automated generation. By leveraging large-scale language models to semantically abstract source code and map it to target languages, this study explores its potential to improve migration accuracy, reduce manual intervention, and ensure system compatibility. Experiments indicate that this technology can optimize migration workflows, enhance code consistency and test coverage, and provide effective support for the stable operation of software systems in multi-language environments. The findings highlight that generative AI offers a novel technical approach and methodological support for cross-language migration and compatibility testing.
Keyword
Artificial Intelligence; Code Migration; Compatibility Testing; Software Engineering
References
[1] Zhang L, Luo S, Pan L, et al. FSD-CLCD: Functional semantic distillation graph learning for cross-language code clone detection. Eng Appl Artif Intell. 2024;133(Pt C):108199.
[2] Yong C, Chao X, Selena JH, et al. A Cross Language Code Security Audit Framework Based on Normalized Representation. J Quantum Comput. 2023;4(2):75-84.
[3] Mehrotra N, Sharma A, Jindal A, et al. Improving Cross-Language Code Clone Detection via Code Representation Learning and Graph Neural Networks. IEEE Trans Softw Eng. 2023;49(11):4846-68.
[4] Yang W, Lin C. Translanguaging with generative AI in EFL writing: Students’ practices and perceptions. J Second Lang Writ. 2025;67:101181.
[5] Lingard L, Klasen J. Qualitative data, cross-language research and AI translation: Three icebergs. Med Educ. 2025;59(6):566-8.
[6] Martinelli C, Giordano A, Carnevale V, et al. The PERFORM Study: Artificial Intelligence Versus Human Residents in Cross-Sectional Obstetrics-Gynecology Scenarios Across Languages and Time Constraints. Mayo Clin Proc Digit Health. 2025;3(2):100206.
[7] Thekdi S, Tatar U, Santos J, et al. On the compatibility of established methods with emerging artificial intelligence and machine learning methods for disaster risk analysis. Risk Anal. 2024;45(4):863-77.
[8] Glascott K, Gomez J, Harkness W, et al. PO-01-014 Interconnectivity and multipolar catheter compatibility with an artificial intelligence software for mapping of atrial fibrillation. Heart Rhythm. 2024;21(5S):S164.
Copyright
© 2025 by the author(s).
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) license, which permits non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and is not modified or adapted.
https://creativecommons.org/licenses/by-nc-nd/4.0/
How to cite this paper
Analysis of Implementation Pathways for Generative AI in Cross-language Code Migration and Compatibility Testing
How to cite this paper: Zhenlin Jin. (2025) Analysis of Implementation Pathways for Generative AI in Cross-language Code Migration and Compatibility Testing. Advances in Computer and Communication, 6(4), 256-261.
DOI: http://dx.doi.org/10.26855/acc.2025.10.017