JETIA/
Articles/
2609005210
  • Open Access
  • Review

Generative AI for Software Engineering: A Review of Code Generation, Testing, Human–AI Collaboration, and Quality Assurance

  • Yang Lu

Received: 22 July 2026 | Revised: 21 August 2026 | Accepted: 30 October 2026 | Published: 05 November 2026

Abstract

Generative AI is increasingly reshaping software engineering (SE) across the development lifecycle. This review synthesises 113 peer-reviewed journal studies and organises the literature around five research questions and four application areas: code generation, testing and debugging, human–AI collaboration, and quality assurance. The reviewed studies show substantial progress in natural-language-to-code generation, context-aware programming, automated testing, fault localisation, program repair, and AI-assisted development. At the same time, persistent challenges remain in semantic correctness, non-deterministic outputs, software security, maintainability, verification, and evaluation consistency. Drawing these findings together, the paper presents a lifecycle mapping, a closed-loop AI-driven software engineering framework, and a four-dimension taxonomy to organise existing research and clarify connections across previously fragmented areas. Overall, generative AI is moving software engineering from a largely deterministic and human-centred workflow toward a more probabilistic and AI-enhanced engineering process. Further progress will depend on stronger verification, security, reliability, maintainability, and appropriately calibrated human oversight.

References 

  • 1.

    Gao, C.; Hu, X.; Gao, S.; et al. The Current Challenges of Software Engineering in the Era of Large Language Models. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–30. https://doi.org/10.1145/3712005.

  • 2.

    Zhang, S.; Xing, Z.; Guo, R.; et al. Empowering Agile-Based Generative Software Development through Human-AI Teamwork. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–46. https://doi.org/10.1145/3702987.

  • 3.

    Ahmed, M.A.; Anwar, M.W.; Butt, W.H.; et al. VeriGen: An LLM-Augmented Framework for End-to-End Automation of Software Development Lifecycle–From Requirements Specifications to Code Generation. IEEE Access 2026, 14, 63962–63990. https://doi.org/10.1109/access.2026.3686308.

  • 4.

    Terragni, V.; Vella, A.; Roop, P.; et al. The Future of AI-Driven Software Engineering. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–20. https://doi.org/10.1145/3715003.

  • 5.

    Jiang, J.; Wang, F.; Shen, J.; et al. A Survey on Large Language Models for Code Generation. ACM Trans. Softw. Eng. Methodol. 2026, 35, 1–72. https://doi.org/10.1145/3747588.

  • 6.

    Truong, J.; Nguyen, V.; Nguyen, T.T. An overview of evaluation and enhancement methods for code generation by large language models. Inf. Softw. Technol. 2026, 197, 108185. https://doi.org/10.1016/j.infsof.2026.108185.

  • 7.

    Faraji, A.; Pombo, N. AI-Driven Software Test Automation: An AI4SE-Oriented Survey of Techniques, Tools, and Challenges. IEEE Access 2025, 13, 183296–183313. https://doi.org/10.1109/access.2025.3623944.

  • 8.

    Almanasra, S.; Suwais, K. Analysis of ChatGPT-Generated Codes Across Multiple Programming Languages. IEEE Access 2025, 13, 23580–23596. https://doi.org/10.1109/access.2025.3538050.

  • 9.

    Tang, Y.; Liu, Z.; Zhou, Z.; et al. ChatGPT vs SBST: A Comparative Assessment of Unit Test Suite Generation. IEEE Trans. Softw. Eng. 2024, 50, 1340–1359. https://doi.org/10.1109/tse.2024.3382365.

  • 10.

    Dakhel, A.M.; Nikanjam, A.; Majdinasab, V.; et al. Effective test generation using pre-trained Large Language Models and mutation testing. Inf. Softw. Technol. 2024, 171, 107468. https://doi.org/10.1016/j.infsof.2024.107468.

  • 11.

    Zhou, X.; Liang, P.; Zhang, B.; et al. Exploring the problems, their causes and solutions of AI pair programming: A study on GitHub and Stack Overflow. J. Syst. Softw. 2025, 219, 112204. https://doi.org/10.1016/j.jss.2024.112204.

  • 12.

    Sun, X.; Ståhl, D.; Sandahl, K.; et al. Quality assurance of LLM-generated code: Addressing non-functional quality characteristics. J. Syst. Softw. 2026, 238, 112885. https://doi.org/10.1016/j.jss.2026.112885.

  • 13.

    Zheng, Z.; Ning, K.; Zhong, Q.; et al. Towards an understanding of large language models in software engineering tasks. Empir. Softw. Eng. 2025, 30, 50. https://doi.org/10.1007/s10664-024-10602-0.

  • 14.

    Dong, Y.; Ding, J.; Jiang, X.; et al. CodeScore: Evaluating Code Generation by Learning Code Execution. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–22. https://doi.org/10.1145/3695991.

  • 15.

    Basha, M.; Rodríguez-Pérez, G. Trust, transparency, and adoption in generative AI for software engineering: Insights from Twitter discourse. Inf. Softw. Technol. 2025, 186, 107804. https://doi.org/10.1016/j.infsof.2025.107804.

  • 16.

    Walczak, J.; Tomalak, P.; Laskowski, A. Impact of code context and prompting strategies on automated unit test generation with modern general-purpose large language models. J. Syst. Softw. 2026, 237, 112834. https://doi.org/10.1016/j.jss.2026.112834.

  • 17.

    Pendyala, V.S.; Thakur, N.B. Performance and interpretability analysis of code generation large language models. Neurocomputing 2025, 656, 131461. https://doi.org/10.1016/j.neucom.2025.131461.

  • 18.

    Tambon, F.; Moradi-Dakhel, A.; Nikanjam, A.; et al. Bugs in large language models generated code: An empirical study. Empir. Softw. Eng. 2025, 30, 65. https://doi.org/10.1007/s10664-025-10614-4.

  • 19.

    Liu, F.; Liu, Y.; Shi, L.; et al. Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code. IEEE Trans. Softw. Eng. 2026, 52, 1037–1055. https://doi.org/10.1109/tse.2026.3657432.

  • 20.

    Otoum, N.; Elkhalili, N. Methods and Techniques of Agentic Software Engineering: A Systematic Literature Review. IEEE Access 2026, 14, 7443–7465. https://doi.org/10.1109/access.2026.3652325.

  • 21.

    Ljaljevic, S.; Jorba, J.; Iserte, S. Exploring the role of Large Language Models in High-Performance Computing programming: A survey. Future Gener. Comput. Syst. 2026, 184, 108618. https://doi.org/10.1016/j.future.2026.108618.

  • 22.

    Valdivia, J.; Mauricio, D.; Guzmán-Jiménez, R. Generative Artificial Intelligence for Software Development Using ISO/IEC 29110 Basic Profile: Gaps and Opportunities. IEEE Access 2026, 14, 31358–31377. https://doi.org/10.1109/access.2026.3659713.

  • 23.

    Liu, S.; Guo, D.; Zhang, J.; et al. An Empirical Study of Exploring the Capabilities of Large Language Models in Code Learning. IEEE Trans. Softw. Eng. 2025, 51, 3088–3102. https://doi.org/10.1109/tse.2025.3609876.

  • 24.

    Yang, G.; Zhou, Y.; Chen, X.; et al. Chain-of-Thought in Neural Code Generation: From and for Lightweight Language Models. IEEE Trans. Softw. Eng. 2024, 50, 2437–2457. https://doi.org/10.1109/tse.2024.3440503.

  • 25.

    Liu, J.; Li, S.; Liu, Z.; et al. Towards multi-language repository-level code generation: From-scratch to guided tasks. Neurocomputing 2026, 679, 133204. https://doi.org/10.1016/j.neucom.2026.133204.

  • 26.

    Weyssow, M.; Zhou, X.; Kim, K.; et al. Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–25. https://doi.org/10.1145/3714461.

  • 27.

    Mahade Hasan, M.; Waseem, M.; Kemell, K.K.; et al. Assessing small language models for code generation: An empirical study with benchmarks. J. Syst. Softw. 2026, 236, 112815. https://doi.org/10.1016/j.jss.2026.112815.

  • 28.

    Nguyen, T.T.; Vu, T.T.; Vo, H.D.; et al. An empirical study on capability of Large Language Models in understanding code semantics. Inf. Softw. Technol. 2025, 185, 107780. https://doi.org/10.1016/j.infsof.2025.107780.

  • 29.

    Li, Y.; Shi, J.; Zhang, Z. An Approach for Rapid Source Code Development Based on ChatGPT and Prompt Engineering. IEEE Access 2024, 12, 53074–53087. https://doi.org/10.1109/access.2024.3385682.

  • 30.

    Liu, Z.; Tang, Y.; Luo, X.; et al. No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT. IEEE Trans. Softw. Eng. 2024, 50, 1548–1584. https://doi.org/10.1109/tse.2024.3392499.

  • 31.

    Lin, Z.; Liu, Z.; Zhou, M.; et al. Effective Fine-tuning for Low-resource Languages: A Case Study of Cangjie. Empir. Softw. Eng. 2026, 31, 150. https://doi.org/10.1007/s10664-026-10878-4.

  • 32.

    Li, S.; Cheng, Y.; Chen, J.; et al. Performance analysis of AI-generated code: A case study of Copilot, Copilot Chat, CodeLlaMa, and DeepSeek-Coder models. Empir. Softw. Eng. 2026, 31, 62. https://doi.org/10.1007/s10664-025-10776-1.

  • 33.

    Shi, Y.; Bangash, A.A.; Fallahzadeh, E.; et al. HAFix: History-augmented large language models for bug fixing. Empir. Softw. Eng. 2026, 31, 104. https://doi.org/10.1007/s10664-026-10833-3.

  • 34.

    Kang, S.; Yoon, J.; Askarbekkyzy, N.; et al. Evaluating Diverse Large Language Models for Automatic and General Bug Reproduction. IEEE Trans. Softw. Eng. 2024, 50, 2677–2694. https://doi.org/10.1109/tse.2024.3450837.

  • 35.

    Newcomb, L.; Newcomb, A.; Ochoa, O. Preconditions and Postconditions as Design Constraints for LLM Code Generation. IEEE Access 2025, 13, 184259–184274. https://doi.org/10.1109/access.2025.3625819.

  • 36.

    Zhang, B.; Zhang, L.; Luo, Z.; et al. Are They All Good? Evaluating the Quality of CoTs in LLM-Based Code Generation. IEEE Trans. Softw. Eng. 2026, 52, 1928–1943. https://doi.org/10.1109/tse.2026.3676295.

  • 37.

    Ouyang, S.; Zhang, J.M.; Harman, M.; et al. An Empirical Study of the Non-Determinism of ChatGPT in Code Generation. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–28. https://doi.org/10.1145/3697010.

  • 38.

    Bui, T.D.; Vu, T.T.; Nguyen, T.T.; et al. Correctness assessment of code generated by Large Language Models using internal representations. J. Syst. Softw. 2025, 230, 112570. https://doi.org/10.1016/j.jss.2025.112570.

  • 39.

    Costa, L.A.; Fontão, A.; Santos, R.P.D.; et al. Applying generative artificial intelligence for vulnerability fixing in a proprietary software ecosystem. J. Syst. Softw. 2026, 234, 112723. https://doi.org/10.1016/j.jss.2025.112723.

  • 40.

    Qian, X.; AlOmar, E.A. Can large language models identify and refactor code clones? An empirical study. J. Syst. Softw. 2026, 234, 112717. https://doi.org/10.1016/j.jss.2025.112717.

  • 41.

    Dong, Y.; Jiang, X.; Jin, Z.; et al. Self-Collaboration Code Generation via ChatGPT. ACM Trans. Softw. Eng. Methodol. 2024, 33, 1–38. https://doi.org/10.1145/3672459.

  • 42.

    Ahmad, A.; Naeem, M. Boosting Test Generation in Industrial Codebases: A Comparative Study of Base and Fine-Tuned LLMs. IEEE Access 2026, 14, 73436–73454. https://doi.org/10.1109/access.2026.3690571.

  • 43.

    Zhu, Y.; Liu, C.; He, X.; et al. AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation. IEEE Trans. Softw. Eng. 2026, 52, 631–650. https://doi.org/10.1109/tse.2025.3642621.

  • 44.

    Ye, S.; Sun, Z.; Wang, G.; et al. Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation. IEEE Trans. Softw. Eng. 2025, 51, 2472–2493. https://doi.org/10.1109/tse.2025.3589634.

  • 45.

    Khojah, R.; de Oliveira Neto, F.G.; Mohamad, M.; et al. The Impact of Prompt Programming on Function-Level Code Generation. IEEE Trans. Softw. Eng. 2025, 51, 2381–2395. https://doi.org/10.1109/tse.2025.3587794.

  • 46.

    Zhao, J.; Sun, Y.; Huang, C.; et al. Towards Secure Code Generation with LLMs: A Study on Common Weakness Enumeration. IEEE Trans. Softw. Eng. 2025, 51, 3507–3523. https://doi.org/10.1109/tse.2025.3619281.

  • 47.

    Palla, D.; Slaby, A. Evaluation of Generative AI Models in Python Code Generation: A Comparative Study. IEEE Access 2025, 13, 65334–65347. https://doi.org/10.1109/access.2025.3560244.

  • 48.

    Ságodi, Z.; Siket, I.; Ferenc, R. Methodology for Code Synthesis Evaluation of LLMs Presented by a Case Study of ChatGPT and Copilot. IEEE Access 2024, 12, 72303–72316. https://doi.org/10.1109/access.2024.3403858.

  • 49.

    Rizqullah, M.; Albassam, E. Model-Agnostic Empirical Evaluation of Test-Driven Prompt Engineering on Improving Accuracy and Efficiency in Large Language Models Python Code Generation. IEEE Access 2026, 14, 22801–22821. https://doi.org/10.1109/access.2026.3662817.

  • 50.

    Esnaola, L.M.; Ramón, H.D.; Lanzarini, L.C. Can generative AI bridge the gap? A quasi-experimental study of non-programmers with AI vs. programmers without AI. Empir. Softw. Eng. 2026, 31, 75. https://doi.org/10.1007/s10664-026-10813-7.

  • 51.

    Chan, P.Y.P.; Keung, J.; Yang, Z. Effectiveness of symmetric metamorphic relations on validating the stability of code generation LLM. J. Syst. Softw. 2025, 222, 112330. https://doi.org/10.1016/j.jss.2024.112330.

  • 52.

    Yang, G.; Zhou, Y.; Cheng, W.; et al. Less Is More: DocString Compression in Code Generation. ACM Trans. Softw. Eng. Methodol. 2026, 35, 1–31. https://doi.org/10.1145/3735636.

  • 53.

    Dong, Y.; Kong, L.; Zhang, L.; et al. A search-and-fill strategy to code generation for complex software requirements. Inf. Softw. Technol. 2025, 177, 107584. https://doi.org/10.1016/j.infsof.2024.107584.

  • 54.

    Delgado, D.; Burgueño, L.; Clarisó, R. A framework for assessing the capabilities of code generation of constraint domain-specific languages with large language models. J. Syst. Softw. 2026, 238, 112871. https://doi.org/10.1016/j.jss.2026.112871.

  • 55.

    Ko, A.J.; Myers, B.A.; Coblenz, M.; et al. A Retrospective on How Developers Seek, Relate, and Collect Information About Code. IEEE Trans. Softw. Eng. 2025, 51, 848–851. https://doi.org/10.1109/tse.2025.3534071.

  • 56.

    Patel, M.S.; Dhawan, R.; Bramhanwade, L.; et al. Code Comprehension Gaps in AI-Assisted Development: A Conceptual Framework for Knowledge Erosion Patterns. IEEE Access 2026, 14, 66740–66757. https://doi.org/10.1109/access.2026.3689574.

  • 57.

    Bhandari, G.; Gavric, N.; Shalaginov, A. Generating vulnerability security fixes with Code Language Models. Inf. Softw. Technol. 2025, 185, 107786. https://doi.org/10.1016/j.infsof.2025.107786.

  • 58.

    Ahn, J.; Lee, S.; Kang, S. An MCP Tool for Bug Localization by Leveraging Modification Frequencies of Similar Bug Reports. IEEE Access 2026, 14, 25242–25263. https://doi.org/10.1109/access.2026.3665337.

  • 59.

    Balim, C.; Karasekreter, N.; Aslan, Ö. Automatic multi-language analysis of SOLID compliance via machine learning algorithms. Inf. Softw. Technol. 2026, 192, 108013. https://doi.org/10.1016/j.infsof.2026.108013.

  • 60.

    Yu, X.; Liu, L.; Hu, X.; et al. Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks? IEEE Trans. Softw. Eng. 2024, 50, 3435–3453. https://doi.org/10.1109/tse.2024.3492204.

  • 61.

    Zhuo, T.Y.; He, J.; Sun, J.; et al. Identifying and Mitigating API Misuse in Large Language Models. IEEE Trans. Softw. Eng. 2026, 52, 855–873. https://doi.org/10.1109/tse.2026.3651566.

  • 62.

    Trong Vu, T.; Bui, T.D.; Nguyen, T.T.; et al. Model-agnostic quality assessment for LLM-generated code via dynamic internal representation selection. J. Syst. Softw. 2026, 237, 112852. https://doi.org/10.1016/j.jss.2026.112852.

  • 63.

    Li, X.; Yuan, S.; Gu, X.; et al. Few-shot code translation via task-adapted prompt learning. J. Syst. Softw. 2024, 212, 112002. https://doi.org/10.1016/j.jss.2024.112002.

  • 64.

    De Siano, G.D.; Fasolino, A.R.; Sperlí, G.; et al. Translating code with Large Language Models and human-in-the-loop feedback. Inf. Softw. Technol. 2025, 186, 107785. https://doi.org/10.1016/j.infsof.2025.107785.

  • 65.

    Zhao, Z.; Fard, F. Do Current Language Models Support Code Intelligence for R Programming Language? ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–39. https://doi.org/10.1145/3735635.

  • 66.

    Eagal, A.; Stolee, K.; Ore, J. Analyzing the dependability of Large Language Models for code clone generation. J. Syst. Softw. 2025, 230, 112548. https://doi.org/10.1016/j.jss.2025.112548.

  • 67.

    Umer, M.M. Comparative Analysis of the Code Generated by Popular Large Language Models (LLMs) for MISRA C++ Compliance. IEEE Access 2025, 13, 194815–194831. https://doi.org/10.1109/access.2025.3633086.

  • 68.

    Tony, C.; Díaz Ferreyra, N.E.; Mutas, M.; et al. Prompting Techniques for Secure Code Generation: A Systematic Investigation. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–53. https://doi.org/10.1145/3722108.

  • 69.

    Huang, L.; Yan, M.; Yin, T.; et al. Steer Your Model: Secure Code Generation with Contrastive Decoding. IEEE Trans. Softw. Eng. 2026, 52, 809–834. https://doi.org/10.1109/tse.2025.3650127.

  • 70.

    Li, D.; Shu, S.; Yan, M.; et al. Improving Co-Decoding Based Security Hardening of Code LLMs Leveraging Knowledge Distillation. IEEE Trans. Softw. Eng. 2025, 51, 2634–2650. https://doi.org/10.1109/tse.2025.3591791.

  • 71.

    Wang, Q.; Wang, J.; Li, M.; et al. A Roadmap for Software Testing in Open-Collaborative and AI-Powered Era. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–17. https://doi.org/10.1145/3709355.

  • 72.

    Kumar, C.; Sri Ponaka, U.; Naidu, P.V.L.N.; et al. AI-Powered Unit Test Generation via Multi-LLM Chaining: A Case Study With GPT-4o, Gemini, and Claude-3.5. IEEE Access 2025, 13, 204058–204071. https://doi.org/10.1109/access.2025.3637221.

  • 73.

    Yang, Z.; Wang, L. IntelliUnitGen: A Unit Test Case Generation Framework Based on the Integration of Static Analysis and Prompt Learning. IEEE Access 2025, 13, 177760–177784. https://doi.org/10.1109/access.2025.3615990.

  • 74.

    Alagarsamy, S.; Tantithamthavorn, C.; Takerngsaksiri, W.; et al. Enhancing large language models for text-to-testcase generation. J. Syst. Softw. 2025, 230, 112531. https://doi.org/10.1016/j.jss.2025.112531.

  • 75.

    Trong, M.P.; Tung Son, N.; Hai, L.N.; et al. A Business Process-Centric Approach for LLM-Driven Functional Test Generation. IEEE Access 2026, 14, 44120–44146. https://doi.org/10.1109/access.2026.3671629.

  • 76.

    Sisomboon, W.; Kaewyotha, J.; Songpan, W. Automated Software Test Case Generation Using Directional Partially Weighted Ensemble Large Language Models with Retrieval-Augmented Generation (RAG). IEEE Access 2026, 14, 31124–31145. https://doi.org/10.1109/access.2026.3667925.

  • 77.

    Karpurapu, S.; Myneni, S.; Nettur, U.; et al. Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation. IEEE Access 2024, 12, 58715–58721. https://doi.org/10.1109/access.2024.3391815.

  • 78.

    Liu, Z.; Wang, H.; Xu, T.; et al. RAG-Driven multiple assertions generation with large language models. Empir. Softw. Eng. 2025, 30, 105. https://doi.org/10.1007/s10664-025-10641-1.

  • 79.

    Haldar, S.; Pierce, M.; Fernando Capretz, L. Exploring the Integration of Generative AI Tools in Software Testing Education: A Case Study on ChatGPT and Copilot for Preparatory Testing Artifacts in Postgraduate Learning. IEEE Access 2025, 13, 46070–46090. https://doi.org/10.1109/access.2025.3545882.

  • 80.

    Mehmood, A.; Ilyas, Q.M.; Ahmad, M.; et al. Test Suite Optimization Using Machine Learning Techniques: A Comprehensive Study. IEEE Access 2024, 12, 168645–168671. https://doi.org/10.1109/access.2024.3490453.

  • 81.

    Fraser, G.; Arcuri, A. A Retrospective on Whole Test Suite Generation: On the Role of SBST in the Age of LLMs. IEEE Trans. Softw. Eng. 2025, 51, 874–878. https://doi.org/10.1109/tse.2025.3539458.

  • 82.

    Ouédraogo, W.C.; Plein, L.; Kaboré, K.; et al. Enriching automatic test case generation by extracting relevant test inputs from bug reports. Empir. Softw. Eng. 2025, 30, 85. https://doi.org/10.1007/s10664-025-10635-z.

  • 83.

    Luo, Z.; Du, Q.; Wang, Y.; et al. Enhancing Protocol Fuzzing via Diverse Seed Corpus Generation. IEEE Trans. Softw. Eng. 2025, 51, 2693–2709. https://doi.org/10.1109/tse.2025.3595396.

  • 84.

    Nettur, S.B.; Karpurapu, S.; Nettur, U.; et al. Cypress Copilot: Development of an AI Assistant for Boosting Productivity and Transforming Web Application Testing. IEEE Access 2025, 13, 3215–3229. https://doi.org/10.1109/access.2024.3521407.

  • 85.

    Fan, X.; Hu, J.; Zheng, W.; et al. SLMFL: Structural and semantic fusion for fault localization based on Small Language Models. Inf. Softw. Technol. 2026, 196, 108143. https://doi.org/10.1016/j.infsof.2026.108143.

  • 86.

    Yin, X.; Ni, C.; Li, X.; et al. Improving the ability of pre-trained language model by imparting large language model’s experience. J. Syst. Softw. 2026, 234, 112744. https://doi.org/10.1016/j.jss.2025.112744.

  • 87.

    Wang, D.S.; Kim, T.I.; Lee, C.G.; et al. Automated Logging with Large Language Models: Eliminating Task-Specific Pretraining. IEEE Access 2025, 13, 213260–213272. https://doi.org/10.1109/access.2025.3645237.

  • 88.

    Zhang, J.; Liao, J.; Tang, J.; et al. The Power of Small LLMs: A Multi-Agent for Code Generation via Dynamic Precaution Tuning. IEEE Trans. Softw. Eng. 2026, 52, 86–99. https://doi.org/10.1109/tse.2025.3632508.

  • 89.

    Ságodi, Z.; Kolláth, I.; Hegedűs, P.; et al. A Program Synthesis Dataset for LLM Temperature Analysis. IEEE Access 2025, 13, 184022–184029. https://doi.org/10.1109/access.2025.3625443.

  • 90.

    Altin, M.; Mutlu, B.; Kilinc, D.; et al. Automated Testing for Service-Oriented Architecture: Leveraging Large Language Models for Enhanced Service Composition. IEEE Access 2025, 13, 89627–89640. https://doi.org/10.1109/access.2025.3571994.

  • 91.

    Lin, Z.; Ma, W.; Lin, T.; et al. Open Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning. ACM Trans. Softw. Eng. Methodol. 2025, 34, 1–24. https://doi.org/10.1145/3708529.

  • 92.

    Russo, D. Navigating the Complexity of Generative AI Adoption in Software Engineering. ACM Trans. Softw. Eng. Methodol. 2024, 33, 1–50. https://doi.org/10.1145/3652154.

  • 93.

    Mailach, A.; Gorgosch, D.; Siegmund, N.; et al. “Ok Pal, we have to code that now”: Interaction patterns of programming beginners with a conversational chatbot. Empir. Softw. Eng. 2025, 30, 34. https://doi.org/10.1007/s10664-024-10561-6.

  • 94.

    Ogenrwot, D.; Businge, J. PatchTrack: A comprehensive analysis of ChatGPT’s influence on pull request outcomes. Empir. Softw. Eng. 2026, 31, 136. https://doi.org/10.1007/s10664-026-10869-5.

  • 95.

    Ko, E.; Kang, P. Evaluating Coding Proficiency of Large Language Models: An Investigation Through Machine Learning Problems. IEEE Access 2025, 13, 52925–52938. https://doi.org/10.1109/access.2025.3553870.

  • 96.

    Nashaat, M.; Miller, J. Towards Efficient Fine-Tuning of Language Models with Organizational Data for Automated Software Review. IEEE Trans. Softw. Eng. 2024, 50, 2240–2253. https://doi.org/10.1109/tse.2024.3428324.

  • 97.

    Gəruslu, V.; Jafarov, Z.; Mövsümova, A.; et al. Encouraging responsible GenAI use in software engineering education: A design-oriented model. J. Syst. Softw. 2026, 237, 112846. https://doi.org/10.1016/j.jss.2026.112846.

  • 98.

    Li, L.; Duan, L. Human centric innovation at the heart of industry 5.0—exploring research challenges and opportunities. Int. J. Prod. Res. 2026, 64, 4901–4933. https://doi.org/10.1080/00207543.2025.2462657.

  • 99.

    Liu, Z.; Zeng, R.; Wang, D.; et al. Agents4PLC: Automating Closed-Loop PLC Code Generation and Verification in Industrial Control Systems Using LLM-Based Agents. IEEE Trans. Softw. Eng. 2026, 52, 1672–1687. https://doi.org/10.1109/tse.2026.3667895.

  • 100.

    Fahad, I.A.; Fuad, M.M.N. Can we trust the source? A systematic review of watermarking and attribution for AI-generated code. Inf. Softw. Technol. 2026, 196, 108157. https://doi.org/10.1016/j.infsof.2026.108157.

  • 101.

    Martins, M.; Jardim, B.; De Castro Neto, M.; et al. Talking to Data: A Systematic Review of the Rise of Conversational Agents for Visual Analytics. IEEE Access 2025, 13, 208902–208931. https://doi.org/10.1109/access.2025.3638950.

  • 102.

    Li, J.; Fu, L.; Wang, Y. Generative AI and management analytics: survey. J. Manag. Anal. 2026, 13, 217–263. https://doi.org/10.1080/23270012.2026.2652312.

  • 103.

    Weyssow, M.; Kamanda, A.; Zhou, X.; et al. CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences. ACM Trans. Softw. Eng. Methodol. 2026, 35, 1–36. https://doi.org/10.1145/3736407.

  • 104.

    Jonnala, R.; Yang, J.; Lee, Y.; et al. Measuring and Improving the Efficiency of Python Code Generated by LLMs Using CoT Prompting and Fine-Tuning. IEEE Access 2025, 13, 119657–119681. https://doi.org/10.1109/access.2025.3585742.

  • 105.

    Antal, G.; Értekes, L.; Szolnoki, N.; et al. Evaluating Retrieval-Augmented Generation for LLM-Based Vulnerability Detection: An Empirical Study on Real-World Java Vulnerabilities. IEEE Access 2026, 14, 50878–50891. https://doi.org/10.1109/access.2026.3676577.

  • 106.

    Tunzina, T.; Mashira, M.; Islam, M.M. GreenAI: A Comparative Analysis of Environmental Efficiency in LLM-Generated Code. IEEE Access 2026, 14, 18654–18672. https://doi.org/10.1109/access.2026.3658813.

  • 107.

    Liang, Q.; Zhang, Z.; Liu, C.; et al. Condor: A Code Discriminator Integrating General Semantics with Code Details. IEEE Trans. Softw. Eng. 2025, 51, 3524–3539. https://doi.org/10.1109/tse.2025.3620145.

  • 108.

    Liang, Q.; Sun, Z.; Zhao, Y.; et al. Bipartite-Grammar–Aware Pretraining for XML-SQL Code Updating. ACM Trans. Softw. Eng. Methodol. 2026, 35, 1–26. https://doi.org/10.1145/3731752.

  • 109.

    Liu, Y.; Foundjem, A.; Khomh, F.; et al. Adversarial attack classification and robustness testing for large language models for code. Empir. Softw. Eng. 2025, 30, 154. https://doi.org/10.1007/s10664-025-10693-3.

  • 110.

    Wang, Z. CurricuForge: A Unified Framework for Progressive Code Generation Through Curriculum-Guided Multi-Agent Collaboration with Symbolic Verification. IEEE Access 2026, 14, 32557–32573. https://doi.org/10.1109/access.2026.3668847.

  • 111.

    Liao, Y.; Zhang, J.; Keung, J.; et al. Advancing autonomous driving system testing: Demands, challenges, and future directions. Inf. Softw. Technol. 2025, 187, 107859. https://doi.org/10.1016/j.infsof.2025.107859.

  • 112.

    Wu, J.; Jiang, Y.; Wei, L.; et al. Question Selection for Multimodal Code Search Synthesis Using Probabilistic Version Spaces. IEEE Trans. Softw. Eng. 2025, 51, 1724–1744. https://doi.org/10.1109/tse.2025.3565387.

  • 113.

    Chen, W.C.; Chen, S.Y. TIPS: A Prompt Engineering Framework for Code Classification and Generation on Resource-Constrained Systems. IEEE Access 2026, 14, 15723–15735. https://doi.org/10.1109/access.2026.3658502.

  • 114.

    Lim, S.C.; Kim, J.C. Hybrid Quantum-Classical Transfer Learning for Parameter-Efficient Code Generation. IEEE Access 2026, 14, 65357–65373. https://doi.org/10.1109/access.2026.3687852.

  • 115.

    Sun, Y.; Li, L.; Yu, Z.; et al. Exploring AI models and applications within a system framework. Syst. Res. Behav. Sci. 2025, 42, 1163–1180. https://doi.org/10.1002/sres.3036.

  • 116.

    Kang, Y.; Pu, B.; Kou, Y.; et al. A deep graph network with multiple similarity for user clustering in human–computer interaction. ACM Trans. Multimed. Comput. Commun. Appl. 2024, 20, 1–20. https://doi.org/10.1145/3549954.

Share this article:
Download PDF
DOI
10.53941/jetia.2026.100010
Issue
Volume 1, Issue 2
How to Cite
Lu, Y. Generative AI for Software Engineering: A Review of Code Generation, Testing, Human–AI Collaboration, and Quality Assurance. Journal of Emerging Technologies with Industrial Applications 2026, 1 (2), 10. https://doi.org/10.53941/jetia.2026.100010.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2026 by the authors.
Article Metrics
23
Article Views
0
Citations