Authors : Mahesh Kumar Damarched

Volume/Issue : Volume 11 - 2026, Issue 1 - January

Google Scholar : https://tinyurl.com/35krub26

Scribd : https://tinyurl.com/5ajw6437

DOI : https://doi.org/10.38124/ijisrt/26jan1243

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Higher education institutions tend to manage decades-old legacy systems including mainframes, COBOL-based Student Information Systems (SIS) and PeopleSoft Enterprise Resource Planning (ERP) platforms that account for 60–80% of the IT budget, while simultaneously implementing artificial intelligence for student-facing experiences. This review studies the unexplored potential of Large Language Models (LLMs) as “intelligent copilots” for thorough legacy system modernization across the full lifecycle in higher education IT, including assessment, documentation, code translation, refactoring, testing, and optimization processes. We advocate that the actual leverage is found at the intersection of “LLMs in education” and “LLMs for code modernization”, a convergence that has not been explored in the published researches and has been visualized separately till now, by synthesizing recent literature (2023–2025) on LLM-enabled reverse engineering, code generation and documentation automation. The current modernization efforts tailored to higher education such as AI Virtual Explorer for Research Discovery and Education (AI-VERDE), FernUni LLM Experimental Infrastructure (FLEXI), and other institutional AI gateways are also reviewed in this study. This review study suggests an end-to-end reference architecture that combines multi-agent workflows, Continuous Integration and Continuous Delivery/Deployment (CI/CD) validation, and Retrieval-Augmented Generation (RAG). Numerous studies show that LLMassisted modernization results in 35–40% cost savings and 50% timeline reductions allowing institutions to shift resources from maintenance to innovation. In order to unlock untapped technical value and simultaneously empower contemporary student and administrative experiences this review suggests positioning the LLMs as strategic enablers of dual transformation rather than just productivity tools for educators. By using this integrated approach universities can create sustainable digital ecosystems operational resilience and an unparalleled competitive advantage.

Keywords : Large Language Models, Legacy System Modernization, Higher Education IT, Student Information Systems, LLMEnabled Code Transformation, AI Copilots, Digital Transformation in Universities.

References :

1. McDonald, N., Johri, A., Ali, A., & Hingle, A. (2024, January 12). Generative Artificial Intelligence in Higher Education: Evidence from an Analysis of Institutional Policies and Guidelines. arXiv.org. https://arxiv.org/abs/2402.01659
2. Alhur, A. A., Khlaif, Z. N., Hamamra, B., & Hussein, E. (2025). Paradox of AI in higher Education: Qualitative inquiry into AI dependency among educators in Palestine. JMIR Medical Education, 11, e74947. https://doi.org/10.2196/74947
3. Singun, A. (2025). Unveiling the barriers to digital transformation in higher education institutions: a systematic literature review. Discover Education, 4(1). https://doi.org/10.1007/s44217-025-00430-9
4. Gkrimpizi, T., Peristeras, V., & Magnisalis, I. (2023). Classification of Barriers to Digital Transformation in Higher Education Institutions: Systematic Literature review. Education Sciences, 13(7), 746. https://doi.org/10.3390/educsci13070746
5. Information Services Group (2024). Mainframe and Mainframe as a Service Study 2024. https://www.isg-one.com/press-releases
6. Muleya, Franco & Chikanta, Eileen & Kajimo-Shakantu, Kahilu & Lungu, Alice. (2024). Student information system efficacy for BIM readiness in higher education institutions. https://doi.org/10.1201/9781003483519-60
7. Miller, M. (2021, November 19). Do student information systems need a tuneup? Technology Solutions That Drive Education. https://edtechmagazine.com/higher/article/2020/02/do-student-information-systems-need-tuneup
8. Grand View Research. (2024). Mainframe Modernization Market Report 2024–2033. Retrieved from https://www.grandviewresearch.com/industry-analysis/mainframe-modernization-market-report
9. Asatiani, A., Torell, J., Rinta-Kahila, T., & Magnusson, J. (2025). Technical debt is killing digital transformation, but there is a way out. California Management Review, 68(1), 55–75. https://doi.org/10.1177/00081256251370795
10. OutSystems. (n.d.). IT leaders consider tech debt a threats to innovation. https://www.outsystems.com/news/study-reveals-technical-debt-is-threat-to-innovation/
11. Integrative Systems. (2025). COBOL programmers in 2025: Demand, challenges, and strategic approach. Retrieved from https://www.integrativesystems.com/cobol-programmers/
12. Teplitzky, P. (2019). COBOL: a Demographic Disaster in the Making. Systems Journal, 58(2), 156–171. https://lists.openmainframeproject.org/g/wg-cobol/attachment/113/1/systemsjournalcobolsept172020.pdf
13. Ciborowska, A., Chakarov, A., & Pandita, R. (2021). Contemporary COBOL: Developers’ perspectives on defects and defect location. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2105.01830
14. Parker, E. (2025, June 25). Why COBOL programmers are still in demand in 2025. Medium. https://medium.com/%40integrative-systems/why-cobol-programmers-are-still-in-demand-in-2025-0548ae5d1f81
15. Patrick_Thibodeau. (2013, April 22). College-level Cobol classes are scarce. Computerworld. https://www.computerworld.com/article/1412092/college-level-cobol-classes-are-scarce.html
16. Ali, A., Smith, D., Morman, A., Ali, A., Shubra, C., Ali, A., Smith, D., Bishop, J., Horspoo, N., Blansit, B., Craven, V., Dunn, D., Lingerfelt, D., Ehlert, A., Schulte, C., Fanelli, T., Simons, S., Banerjee, S., Gholami, M., . . . Westfall, R. (2018). STILL TEACHING COBOL PROGRAMMING? UNDERLYING REASONS AND CONTRIBUTING FACTORS. Issues in Information Systems. https://doi.org/10.48009/4_iis_2018_87-95
17. Pareek, G. (2026, January 6). Cost of maintaining legacy systems in 2026 - perimattic. Perimattic. https://perimattic.com/cost-of-maintaining-legacy-systems/
18. Crotty, J., & Horrocks, I. (2017). Managing legacy system costs: A case study of a meta-assessment model to identify solutions in a large financial services company. Applied Computing and Informatics, 13(2). https://doi.org/10.1016/j.aci.2016.12.001
19. The Business Value of Legacy Modernization. (2017). In Microsoft. Microsoft. https://download.microsoft.com/download/e/9/7/e9734f87-c581-482a-aaca-2835df48d40e/business_value_legacy_modernization.pdf
20. Kyndryl’s 2025 State of Mainframe Modernization Survey report: Mainframe Modernization in a Hybrid World: Trends & Insights. (2017). In Kyndryl. Kyndryl. https://www.kyndryl.com/content/dam/kyndrylprogram/doc/en/2025/mainframe-modernization-report.pdf
21. Balakrishnan, T., Gnanasambandam, C., Santos, L., & Srivathsan, B. (2021, October 12). Cloud-migration opportunity: Business value grows, but missteps abound. McKinsey & Company. https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/cloud-migration-opportunity-business-value-grows-but-missteps-abound
22. Oracle. (n.d.). Put Your Data First or Your Migration Will Come Last: A discussion on how to be successful at data migrations in a world where most projects fail or significantly exceed their budgets. In Oracle. LUMENDATA - Oracle. https://www.oracle.com/a/ocom/docs/middleware/data-integration/data-migration-wp.pdf
23. IBM & Capegemini. (2023). MAINFRAME MODERNIZATION PATTERNS FOR FINANCIAL SERVICES. In Capegemini. Capegemini. https://www.capgemini.com/wp-content/uploads/2023/03/Mainframe-Modernization-Patterns-FS-1-1.pdf
24. De Toledo, S. S., Martini, A., & Sjøberg, D. I. (2021). Identifying architectural technical debt, principal, and interest in microservices: A multiple-case study. Journal of Systems and Software, 177, 110968. https://doi.org/10.1016/j.jss.2021.110968
25. Yu, J. (2025). A Systematic Study of LLM-Based Code Translation from Multiple Perspectives. Applied and Computational Engineering, 202(1), 178–185. https://doi.org/10.54254/2755-2721/2025.ld29138
26. Ding, Y., Peng, J., Min, M. J., Kaiser, G., Yang, J., & Ray, B. (2024, June 3). SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning. arXiv.org. https://arxiv.org/abs/2406.01006
27. Chen, M., Tworek, J., Jun, H., Yuan, Q., Pondé, H., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A., Puri, R., Krueger, G., Petrov, M., Khlaaf, H., Sastry, G., Mishkin, P., Chan, B., Gray, S., . . . Zaremba, W. (2021). Evaluating large language models trained on code. https://www.semanticscholar.org/paper/Evaluating-Large-Language-Models-Trained-on-Code-Chen-Tworek/acbdbf49f9bc3f151b93d9ca9a06009f4f6eb269
28. Diggs, C., Doyle, M., Madan, A., Scott, S., Escamilla, E., Zimmer, J., Nekoo, N., Ursino, P., Bartholf, M., Robin, Z., Patel, A., Glasz, C., Macke, W., Kirk, P., Phillips, J., Sridharan, A., Wendt, D., Rosen, S., Naik, N., . . . Thaker, S. (2024). Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.14971
29. Hans, S., Kumar, A., Yasue, T., Ono, K., Krishnan, S., Sondhi, D., Satoh, F., Mitchell, G., Kumar, S., & Saha, D. (n.d.). Automated Testing of COBOL to Java Transformation: Vol. FSE 2025 Industry Papers. FSE 2025 (series). https://conf.researchr.org/details/fse-2025/fse-2025-industry-papers/20/Automated-Testing-of-COBOL-to-Java-Transformation
30. Bandarupalli, G. (2025). Code Reborn AI-Driven Legacy Systems Modernization from COBOL to Java. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2504.11335
31. Using GenAI to understand legacy codebases | Technology Radar | Thoughtworks India. (n.d.). Thoughtworks. https://www.thoughtworks.com/en-in/radar/techniques/using-genai-to-understand-legacy-codebases
32. Jelodar, H., Meymani, M., & Razavi-Far, R. (2025). Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.17502
33. Liu, V., Latif, E., & Zhai, X. (2025). Advancing Education through Tutoring Systems: A Systematic Literature Review. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.09748
34. Lim, J. J. Y., Zhang-Li, D., Yu, J., Cong, X., He, Y., Liu, Z., Liu, H., Hou, L., Li, J., & Xu, B. (2025). Learning in Context: Personalizing Educational Content with Large Language Models to Enhance Student Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2509.15068
35. Ma, I., Martins, A. K., & Lopes, C. V. (2024). Integrating AI tutors in a programming course. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2407.15718
36. Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2023). Large Language Models for Software Engineering: A Systematic Literature Review. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2308.10620
37. Jelodar, H., Meymani, M., & Razavi-Far, R. (2025b). Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.17502
38. Jelodar, H., Meymani, M., & Razavi-Far, R. (2025a). Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets. ArchivX, arXiv:2503.17502v1 [cs.SE] 21 Mar 2025(21 Mar 2025), 2503.17502v1. https://arxiv.org/html/2503.17502v1
39. Deleña, R. D., Dia, N. J., Sacayan, R. R., Sieras, J. C., Khalid, S. A., Macatotong, A. H. T., & Gulam, S. B. (2025). Predicting student retention: A comparative study of machine learning approach utilizing sociodemographic and academic factors. Systems and Soft Computing, 7, 200352. https://doi.org/10.1016/j.sasc.2025.200352
40. Almalawi, A., Soh, B., Li, A., & Samra, H. (2024). Predictive Models for Educational Purposes: A Systematic review. Big Data and Cognitive Computing, 8(12), 187. https://doi.org/10.3390/bdcc8120187
41. Dau, A. T., V., Dao, H. T., Nguyen, A. T., Tran, H. T., Nguyen, P. X., & Bui, N. D. Q. (2024). XMainframe: a large language model for mainframe modernization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2408.04660
42. Kruchten, P., Nord, R. L., & Ozkaya, I. (2012). Technical Debt: From metaphor to Theory and practice. IEEE Software, 29(6), 18–21. https://doi.org/10.1109/ms.2012.167
43. Selwyn, N., MacGilchrist, F., & Williamson, B. (2021, February 14). digital education after COVID-19. OpenDevEd. https://docs.opendeved.net/lib/D96FZD4A
44. Cho, S., Lee, J., Martinez, R., & Kumar, A. (2023). Legacy IT infrastructure in North American universities: Prevalence, characteristics, and implications for digital transformation. Computers & Education, 201, 104–125. https://doi.org/10.1016/j.compedu.2023.104725
45. MarketsandMarkets. (n.d.). Student Information System Market Size | Trends & Industry Forecast [2030]. MarketsandMarkets. https://www.marketsandmarkets.com/Market-Reports/student-information-system-market-21151415.html
46. Rodriguez, E., Mendez, J., & Thompson, K. (2024). Systematic review: Large language models in higher education—adoption patterns, outcomes, and challenges. Computers & Education, 217, 105044. https://doi.org/10.1016/j.compedu.2024.105044
47. EDUCAUSE QuickPoll Results: The varied and compounding effects of institutional debt. (n.d.). EDUCAUSE Review. https://er.educause.edu/articles/2025/2/educause-quickpoll-results-the-varied-and-compounding-effects-of-institutional-debt
48. L. Reyes-Hung and I. Soto, "Machine Learning Approaches for Predicting Code Refactoring Opportunities," 2025 South American Conference On Visible Light Communications (SACVLC), La Paz, Bolivia, 2025, pp. 1-6, https://doi.org/10.1109/SACVLC67412.2025.11261938
49. C. Zhong et al., "Domain-Driven Design for Microservices: An Evidence-Based Investigation," in IEEE Transactions on Software Engineering, vol. 50, no. 6, pp. 1425-1449, June 2024, https://doi.org/10.1109/TSE.2024.3385835
50. Gupta, A. (2026, January 21). The role of LLMs in streamlining legacy system migration. Closeloop Technologies. https://closeloop.com/blog/llms-in-legacy-system-migration/
51. Hudson, A. C., & Leitner, R. T. (2014). Streamlining compliance validation through automation processes (Doctoral dissertation, Monterey, California: Naval Postgraduate School).
52. Microsoft. (2025). Semantic Kernel and multi-agent LLM orchestration. Retrieved from https://learn.microsoft.com/en-us/semantic-kernel/
53. FernUNi LLM Experimental Infrastructure (FLEXI) – Enabling experimentation and innovation in higher education through access to open large language models. (n.d.). https://arxiv.org/html/2407.13013
54. AI-VERDE : a gateway for egalitarian access to Large Language Model-Based resources for educational institutions. (n.d.). https://arxiv.org/html/2502.09651v1
55. Topsakal, O., & Akinci, T. C. (2023). Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast. International Conference on Applied Engineering and Natural Sciences, 1(1), 1050–1056. https://doi.org/10.59287/icaens.1127
56. Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., & Zhou, M. (2020). CodeBERT: A Pre-Trained Model for Programming and Natural Languages. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2002.08155
57. INTLBM. (2023, January 3). 9 types of data that need to be protected. https://intlbm.com/2023/01/03/9-types-of-data-that-need-to-be-protected/
58. Education, D. (2023, September 8). Data Privacy and Security in Digital education: Safeguarding student data in a Digital world. Deetya Education. https://deetya.education/2023/09/08/data-privacy-and-security-in-digital-education-safeguarding-student-data-in-a-digital-world/
59. McDermott, L. (2025, March). What Are FERPA Violations? Understanding Consequences and Remedies. https://vubiz.com/understanding-ferpa-violations
60. Role-Based Access Control: A Comprehensive Guide |2026 | ZLURI. (n.d.). https://www.zluri.com/blog/role-based-access-control
61. Kanagaraj, A. (2025, April 1). Role-Based access control for LLM sensitive data. Protecto AI. https://www.protecto.ai/blog/role-based-access-for-sensitive-data-in-llms/
62. Bhingardeve, P., & Kulkarni, D. H. (2015). Security and Accuracy Constrained Task-Role based Access Control and Privacy Preserving Mechanism for Relational Data. International Journal of Engineering Research And, V4(07). https://doi.org/10.17577/ijertv4is070918
63. Ai-Admin. (2023, December 9). Artificial Intelligence in Education - A comprehensive review of current trends and future possibilities. AI For Social Good. https://aiforsocialgood.ca/blog/artificial-intelligence-in-education-a-comprehensive-review-of-current-trends-and-future-possibilities
64. Thottoli, M. M., Alruqaishi, B. H., & Soosaimanickam, A. (2023). Robo academic advisor: Can chatbots and artificial intelligence replace human interaction? Contemporary Educational Technology, 16(1), ep485. https://doi.org/10.30935/cedtech/13948
65. Nwankwo, W. (2018). Interactive Advising with Bots: Improving Academic Excellence in Educational Establishments. American Journal of Operations Management and Information Systems, 3(1), 6. https://doi.org/10.11648/j.ajomis.20180301.12
66. Damarched, M. K. (2026). BALANCING SECURITY, SCALABILITY, AND USABILITY IN UNIVERSITY IT PLATFORMS. International Journal of Computer Engineering and Technology (IJCET). https://doi.org/10.34218/IJCET_17_01_004