Large Language Models in IDEs: Context-Aware Coding, Refactoring, and Documentation
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V4I2P110Keywords:
Large Language Models (LLMs), Integrated Development Environments (IDEs), Code Generation, Developer Productivity, Automated Documentation, Code RefactoringAbstract
The Large Language Models (LLMs) have transformed the process of software development, particularly under the Integrated Development Environments (IDEs). Being trained on large corpora of code and natural language, LLMs have exhibited an extremely high potential to improve the productivity of developers, facilitate the work of code generation, help in refactoring, and automate documentation. The integration of LLMs in IDEs and the consequences of such a step are the topics of this paper and are addressed in three key fields, including context-aware code generation, intelligent code refactoring, and automated documentation. Based on the pre-2023 developments, we access a thorough literature review and construct a systematic approach to assessing productivity and quality enhancement carried out by LLM-based instruments. The paper indicates this transformation in the software development lifecycle using empirical review, case studies, and benchmark results. Moreover, the ethical implications and limitations are mentioned, and the opportunity to conduct further studies about it is discussed. Finally, the paper is expected to become a valuable addition to the body of knowledge available to the researchers and practitioners who might be interested in AI-aided software development
Downloads
References
[1] Bruch, M., Monperrus, M., & Mezini, M. (2009, August). Learning from examples to improve code completion systems. In Proceedings of the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on the foundations of software engineering (pp. 213-222).
[2] Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., ... & Zaremba, W. (2021). Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374.
[3] "CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences" — Maliheh Izadi, Roberta Gismondi, Georgios Gousios; arXiv, February 14, 2022. A language model that enhances code completion by considering both AST token types and naming semantics.
[4] Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877-1901.
[5] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
[6] Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., ... & Sutton, C. (2021). Program synthesis with large language models. arXiv preprint arXiv:2108.07732.
[7] Avizienis, A. (2006). Arithmetic error codes: Cost and effectiveness studies for application in digital system design. IEEE Transactions on Computers, 100(11), 1322-1331.
[8] Ahmad, W. U., Chakraborty, S., Ray, B., & Chang, K. W. (2020). A transformer-based approach for source code summarization. arXiv preprint arXiv:2005.00653.
[9] Allamanis, M., Barr, E. T., Devanbu, P., & Sutton, C. (2018). A survey of machine learning for big code and naturalness. ACM Computing Surveys (CSUR), 51(4), 1-37.
[10] Alizadehsani, Z., Gomez, E. G., Ghaemi, H., González, S. R., Jordan, J., Fernández, A., & Pérez-Lancho, B. (2021, April). Modern Integrated Development Environment (IDEs). In Sustainable Smart Cities and Territories International Conference (pp. 274-288). Cham: Springer International Publishing.
[11] Aghajani, E. (2018, September). Context-aware software documentation. In 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME) (pp. 727-731). IEEE.
[12] Kannan, J., Barnett, S., Cruz, L., Simmons, A., & Agarwal, A. (2022, May). Mlsmellhound: A context-aware code analysis tool. In Proceedings of the ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results (pp. 66-70).
[13] "CoditT5: Pretraining for Source Code and Natural Language Editing" — Jiyang Zhang, Sheena Panthaplackel, Pengyu Nie, Junyi Jessy Li, Milos Gligoric; arXiv, August 10, 2022. A pretrained model tailored for editing tasks like comment updating, bug fixing, and code review.
[14] Aghajani, E., Nagy, C., Vega-Márquez, O. L., Linares-Vásquez, M., Moreno, L., Bavota, G., & Lanza, M. (2019, May). Software documentation issues unveiled. In 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE) (pp. 1199-1210). IEEE.
[15] Sedano, T., Ralph, P., & Péraire, C. (2017, May). Software development waste. In 2017 IEEE/ACM 39th International Conference on Software Engineering (ICSE) (pp. 130-140). IEEE.
[16] "ReACC: A Retrieval-Augmented Code Completion Framework" — Shuai Lu, Nan Duan, Hojae Han, Daya Guo, Seung-won Hwang, Alexey Svyatkovskiy; arXiv, March 15, 2022. Introduces retrieval-augmented completion that leverages external code context.
[17] "A Systematic Evaluation of Large Language Models of Code" — Frank F. Xu, Uri Alon, Graham Neubig, Vincent J. Hellendoorn; arXiv, February 26, 2022. Evaluates code LMs like Codex, GPT-J, GPT-Neo, and introduces PolyCoder.
[18] Wingkvist, A., Ericsson, M., Lincke, R., & Löwe, W. (2010, September). A metrics-based approach to technical documentation quality. In 2010, the Seventh International Conference on the Quality of Information and Communications Technology (pp. 476-481). IEEE.
[19] Berlekamp, E. R. (2005). The technology of error-correcting codes. Proceedings of the IEEE, 68(5), 564-593.
[20] "Better Together? An Evaluation of AI-Supported Code Translation" — Justin D. Weisz, Michael Muller, Steven I. Ross, Fernando Martinez, Stephanie Houde, Mayank Agarwal, Kartik Talamadupula, John T. Richards; IUI ’22, 2022. Evaluates human–AI collaboration in code translation.
[21] Pappula, K. K., & Anasuri, S. (2020). A Domain-Specific Language for Automating Feature-Based Part Creation in Parametric CAD. International Journal of Emerging Research in Engineering and Technology, 1(3), 35-44. https://doi.org/10.63282/3050-922X.IJERET-V1I3P105
[22] Rahul, N. (2020). Vehicle and Property Loss Assessment with AI: Automating Damage Estimations in Claims. International Journal of Emerging Research in Engineering and Technology, 1(4), 38-46. https://doi.org/10.63282/3050-922X.IJERET-V1I4P105
[23] Enjam, G. R., & Tekale, K. M. (2020). Transitioning from Monolith to Microservices in Policy Administration. International Journal of Emerging Research in Engineering and Technology, 1(3), 45-52. https://doi.org/10.63282/3050-922X.IJERETV1I3P106
[24] Pappula, K. K. (2021). Modern CI/CD in Full-Stack Environments: Lessons from Source Control Migrations. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 2(4), 51-59. https://doi.org/10.63282/3050-9262.IJAIDSML-V2I4P106
[25] Pedda Muntala, P. S. R., & Jangam, S. K. (2021). Real-time Decision-Making in Fusion ERP Using Streaming Data and AI. International Journal of Emerging Research in Engineering and Technology, 2(2), 55-63. https://doi.org/10.63282/3050-922X.IJERET-V2I2P108
[26] Rahul, N. (2021). AI-Enhanced API Integrations: Advancing Guidewire Ecosystems with Real-Time Data. International Journal of Emerging Research in Engineering and Technology, 2(1), 57-66. https://doi.org/10.63282/3050-922X.IJERET-V2I1P107
[27] Enjam, G. R., Chandragowda, S. C., & Tekale, K. M. (2021). Loss Ratio Optimization using Data-Driven Portfolio Segmentation. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 2(1), 54-62. https://doi.org/10.63282/3050-9262.IJAIDSML-V2I1P107
[28] Pappula, K. K. (2022). Architectural Evolution: Transitioning from Monoliths to Service-Oriented Systems. International Journal of Emerging Research in Engineering and Technology, 3(4), 53-62. https://doi.org/10.63282/3050-922X.IJERET-V3I4P107
[29] Jangam, S. K. (2022). Role of AI and ML in Enhancing Self-Healing Capabilities, Including Predictive Analysis and Automated Recovery. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 3(4), 47-56. https://doi.org/10.63282/3050-9262.IJAIDSML-V3I4P106
[30] Anasuri, S. (2022). Zero-Trust Architectures for Multi-Cloud Environments. International Journal of Emerging Trends in Computer Science and Information Technology, 3(4), 64-76. https://doi.org/10.63282/3050-9246.IJETCSIT-V3I4P107
[31] Pedda Muntala, P. S. R. (2022). Enhancing Financial Close with ML: Oracle Fusion Cloud Financials Case Study. International Journal of AI, BigData, Computational and Management Studies, 3(3), 62-69. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V3I3P108
[32] Rahul, N. (2022). Optimizing Rating Engines through AI and Machine Learning: Revolutionizing Pricing Precision. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 3(3), 93-101. https://doi.org/10.63282/3050-9262.IJAIDSML-V3I3P110
[33] Enjam, G. R. (2022). Secure Data Masking Strategies for Cloud-Native Insurance Systems. International Journal of Emerging Trends in Computer Science and Information Technology, 3(2), 87-94. https://doi.org/10.63282/3050-9246.IJETCSIT-V3I2P109
