Code-Switching Language Model

Artificial Intelligence (AI) and Large Language Models (LLMs) have significantly transformed software development by enabling intelligent code generation, automated debugging, code translation, and natural language programming. In recent years, AI-assisted Integrated Development Environments (IDEs) have become increasingly capable of improving developer productivity; however, challenges such as limited multilingual support, fragmented development workflows, insufficient explainability, and dependence on cloud infrastructure continue to restrict their broader adoption. This survey reviews recent advances in AI-assisted programming by examining research on code generation, programming-oriented LLMs, intelligent IDEs, multilingual software development, code explanation systems, and educational AI platforms. The strengths, limitations, and emerging research trends reported in the literature are analyzed to identify existing gaps and future opportunities. Based on these findings, the survey discusses the potential of Programming Language Code Switching Language Models (CSLMs) as a promising direction for developing more intelligent, explainable, and multilingual programming environments.

Artificial Intelligence, Large Language Models (LLMs), Code Generation, Code Switching, Integrated Development Environment (IDE)

1. M. Chen et al., “Evaluating Large Language Models Trained on Code,” arXiv:2107.03374, 2021. [Google Scholar] [Crossref]

2. F. Nijkamp et al., “CodeGen: An Open Large Language Model for Code Generation,” arXiv:2203.13474, 2022. [Google Scholar] [Crossref]

3. T. Le et al., “The Stack: 3 TB Dataset of Permissively Licensed Source Code,” arXiv:2211.15533, 2022. [Google Scholar] [Crossref]

4. OpenAI, “GPT-4 Technical Report,” arXiv:2303.08774, 2023. [Google Scholar] [Crossref]

5. B. Rozière et al., “Code Llama: Open Foundation Models for Code,” arXiv:2308.12950, 2023. [Google Scholar] [Crossref]

6. GitHub, “GitHub Copilot Documentation,” 2023. [Online]. Available: https://docs.github.com/en/copilot [Google Scholar] [Crossref]

7. J. Jiang et al., “A Survey on Large Language Models for Code Generation,” arXiv:2406.00515, 2024. [Google Scholar] [Crossref]

8. Y. Guo et al., “DeepSeek-Coder: Advancing Open-Source Code Intelligence,” arXiv:2401.14196, 2024. [Google Scholar] [Crossref]

9. R. Lozhkov et al., “StarCoder2 and The Stack v2: The Next Generation of Open Code Large Language Models,” arXiv:2402.19173, 2024. [Google Scholar] [Crossref]

10. Anthropic, “Claude 3 Model Card,” 2024. [Online]. Available: https://www.anthropic.com/news/claude-3-family [Google Scholar] [Crossref]

11. A. Anand et al., “A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation,” arXiv:2411.07586, 2024. [Google Scholar] [Crossref]

12. S. Bistarelli et al., “Usage of Large Language Model for Code Generation Tasks: A Review,” SN Computer Science, 2025, doi: 10.1007/s42979-025-04241-5. [Google Scholar] [Crossref]

13. N. Huynh and B. Lin, “Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications,” arXiv:2503.01245, 2025. [Google Scholar] [Crossref]

14. B. Gülmez, “Code Generation with Large Language Models: A Survey from Neural Program Synthesis to Autonomous Software Development,” Applied Intelligence, 2026, doi: 10.1007/s10489-026-07230-0. [Google Scholar] [Crossref]

15. “Surveying the Benchmarking Landscape of Large Language Models in Code Intelligence,” ACM Transactions on Software Engineering and Methodology, 2026, doi: 10.1145/3800957. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet