Analysis of the Application and Prospects of Artificial Intelligence in Various Frontend Frameworks
DOI:
https://doi.org/10.61173/ck0pza48Keywords:
Artificial Intelligence, Front-end Frameworks, Large Language Models, Machine Learning, Multi-modal AIAbstract
In recent years, the rapid development of artificial intelligence has influenced software engineering thoroughly. Especially in front-end development, the combination of artificial intelligence with front-end frameworks such as Vue, React and Angular is becoming a significant factor in advancing productivity and developing efficiency. This paper mainly investigates the application mechanism of AI over different front-end frameworks, and also researches the prospects of future development. This study aims to analyze the different aspects of AI integration over several frameworks, comparing their characteristics’ influence on their performance in generating code and converting the layout design into code. Research adopts literature analysis and comparative study, combining existing AI development tools and academic materials. The accuracy, capacity and adaptiveness of AI within the front-end frameworks are discussed in this paper. The findings indicate that AI has established a significant efficiency advantage in front-end development by generating components automatically, optimizing the logic between code, and solving debug errors. However, due to differences in syntax features and data complexity, AI’s effectiveness varies from different front-end frameworks.
References
[1] Chen, Mark et al. “Evaluating Large Language Models Trained on Code.” ArXiv abs/2107.03374 (2021): n. pag.
[2] Si, Chenglei et al. “Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering.” North American Chapter of the Association for Computational Linguistics (2024).
[3] Jiang, Nan et al. “CURE: Code-Aware Neural Machine Translation for Automatic Program Repair.” 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) (2021): 1161-1173.
[4] Yun, Sukmin et al. “Web2Code: A Large-scale Webpageto-Code Dataset and Evaluation Framework for Multimodal LLMs.” ArXiv abs/2406.20098 (2024): n. pag.
[5] Awal, Rabiul et al. “WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation.” ArXiv abs/2508.16763 (2025): n. pag.
[6] Si, Chenglei et al. “Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering.” North American Chapter of the Association for Computational Linguistics (2024).
[7] Sun, Haoyu et al. “FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow.” ArXiv abs/2505.17399 (2025): n. pag.
[8] Prototype2Code: End-to-end Front-end Code Generation (arXiv:2405.04975). arXiv https://arxiv.org/abs/2405.04975
[9] A Survey on Large Language Models for Code Generation (arXiv:2406.00515). arXiv https://arxiv.org/abs/2406.00515
[10] Type-Constrained Code Generation with Language Models (arXiv:2504.09246). arXiv https://arxiv.org/abs/2504.09246
[11] Xiao, Jingyu et al. “DesignBench: A Comprehensive Dean&Francis ISSN 2959-6157 Benchmark for MLLM-based Front-end Code Generation.” ArXiv abs/2506.06251 (2025): n. pag.
[12] Radford, Alec et al. “Learning Transferable Visual Models From Natural Language Supervision.” International Conference on Machine Learning (2021).
[13] V. Thada and V. Jaglan, “Comparison of jaccard, dice, cosine similarity coefficient to find best fitness value for web retrieved documents using genetic algorithm,” International Journal of Innovations in Engineering and Technology, vol. 2, no. 4, pp. 202–205, 2013.
[14] Wang, Ruiqi et al. “Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering.” Proc. ACM Softw. Eng. 2 (2025): 1955-1977.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
