Towards a Large Language Model Based Approach for the Management of Requirements Technical Debt
Resumo
This study addresses the challenge of mitigating Requirements Technical Debt (RTD) by proposing an RTD management approach supported by Large Language Models (LLMs). The approach structures automated mechanisms for the identification, characterization, impact analysis, and evolutionary monitoring of debt throughout the software lifecycle. It articulates linguistic, technical, and decision-making aspects, allowing RTD to be treated as a continuous phenomenon that influences product quality, risk, and sustainability. The approach is expected to provide systematic support for RTD detection, prevention, and mitigation activities, based on the analysis of its potential impact and evolution over time.Referências
Barbosa, L., Freire, S., Rios, N., Ramac, R., Taušan, N., Pérez, B., ... & Spínola, R. (2022, August). Organizing the TD management landscape for requirements and requirements documentation debt. In Workshop on Requirements Engineering (WER).
Biazotto, J. P., Feitosa, D., Avgeriou, P., & Nakagawa, E. Y. (2025). Understanding practitioners’ reasoning and requirements for efficient tool support in technical debt management. Empirical Software Engineering, 30(5), 134.
Ernst, N. A. (2012, June). On the role of requirements in understanding and managing technical debt. In 2012 Third International Workshop on Managing Technical Debt (MTD) (pp. 61-64). IEEE.
Fantechi, A., Gnesi, S., & Semini, L. (2023). Rule-based NLP vs ChatGPT in ambiguity detection, a preliminary study. In CEUR Workshop Proceedings (Vol. 3378). CEUR WS.
Frattini, J., Fucci, D., Mendez, D., Spínola, R., Mandić, V., Taušan, N., ... & GonzalezHuerta, J. (2023). An initial theory to understand and manage requirements engineering debt in practice. Information and Software Technology, 159, 107201.
Guilhermino, F., & Lencastre, M. (2026). Leveraging LLMs to mitigate requirements technical debt: Debt types, tools and limitations – A systematic literature review. In press.
Gupta, A. K., Siddiqui, S. T., Qidwai, K. A., Haider, A. S., Khan, H., & Ahmad, M. O. (2022, December). Software Requirement Ambiguity Avoidance Framework (SRAAF) for Selecting Suitable Requirement Elicitation Techniques for Software Projects. In 2022 IEEE International Conference on Current Development in Engineering and Technology (CCET) (pp. 1-6). IEEE.
Habib, M. K., Graziotin, D., & Wagner, S. (2025). ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation. arXiv preprint arXiv:2505.17632.
Koh, S. J., & Chua, F. F. (2023). ReqGo: a semi-automated requirements management tool. International Journal of Technology, 14(4), 713.
Lenarduzzi, V., & Fucci, D. (2019, September). Towards a holistic definition of requirements debt. In 2019 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) (pp. 1-5). IEEE.
Li, Z., Avgeriou, P., & Liang, P. (2015). A systematic mapping study on technical debt and its management. Journal of systems and software, 101, 193-220.
Ramač, R., Mandić, V., Taušan, N., Rios, N., Freire, S., Pérez, B., ... & Spinola, R. (2022). Prevalence, common causes and effects of technical debt: Results from a family of surveys with the IT industry. Journal of Systems and Software, 184, 111114.
Rusdianto, D. S., Fabroyir, H., & Yuhana, U. L. (2024, August). Innovative approaches to impact analysis of requirement changes using llm in software projects. In 2024 IEEE International Symposium on Consumer Technology (ISCT) (pp. 604-610). IEEE.
da Silva, J. F. G., Lencastre, M., & Castro, J. (2024). Modelagem Conceitual de Dívida Técnica na Engenharia de Requisitos. In 25a Workshop em Engenharia de Requisitos (WER 24).
Veizaga, A., Shin, S. Y., & Briand, L. C. (2024). Automated smell detection and recommendation in natural language requirements. IEEE Transactions on Software Engineering, 50(4), 695-720.
Wieringa, R. (2014). Design science methodology for information systems and software engineering. Springer-Verlag Berlin Heidelberg.
Biazotto, J. P., Feitosa, D., Avgeriou, P., & Nakagawa, E. Y. (2025). Understanding practitioners’ reasoning and requirements for efficient tool support in technical debt management. Empirical Software Engineering, 30(5), 134.
Ernst, N. A. (2012, June). On the role of requirements in understanding and managing technical debt. In 2012 Third International Workshop on Managing Technical Debt (MTD) (pp. 61-64). IEEE.
Fantechi, A., Gnesi, S., & Semini, L. (2023). Rule-based NLP vs ChatGPT in ambiguity detection, a preliminary study. In CEUR Workshop Proceedings (Vol. 3378). CEUR WS.
Frattini, J., Fucci, D., Mendez, D., Spínola, R., Mandić, V., Taušan, N., ... & GonzalezHuerta, J. (2023). An initial theory to understand and manage requirements engineering debt in practice. Information and Software Technology, 159, 107201.
Guilhermino, F., & Lencastre, M. (2026). Leveraging LLMs to mitigate requirements technical debt: Debt types, tools and limitations – A systematic literature review. In press.
Gupta, A. K., Siddiqui, S. T., Qidwai, K. A., Haider, A. S., Khan, H., & Ahmad, M. O. (2022, December). Software Requirement Ambiguity Avoidance Framework (SRAAF) for Selecting Suitable Requirement Elicitation Techniques for Software Projects. In 2022 IEEE International Conference on Current Development in Engineering and Technology (CCET) (pp. 1-6). IEEE.
Habib, M. K., Graziotin, D., & Wagner, S. (2025). ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation. arXiv preprint arXiv:2505.17632.
Koh, S. J., & Chua, F. F. (2023). ReqGo: a semi-automated requirements management tool. International Journal of Technology, 14(4), 713.
Lenarduzzi, V., & Fucci, D. (2019, September). Towards a holistic definition of requirements debt. In 2019 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) (pp. 1-5). IEEE.
Li, Z., Avgeriou, P., & Liang, P. (2015). A systematic mapping study on technical debt and its management. Journal of systems and software, 101, 193-220.
Ramač, R., Mandić, V., Taušan, N., Rios, N., Freire, S., Pérez, B., ... & Spinola, R. (2022). Prevalence, common causes and effects of technical debt: Results from a family of surveys with the IT industry. Journal of Systems and Software, 184, 111114.
Rusdianto, D. S., Fabroyir, H., & Yuhana, U. L. (2024, August). Innovative approaches to impact analysis of requirement changes using llm in software projects. In 2024 IEEE International Symposium on Consumer Technology (ISCT) (pp. 604-610). IEEE.
da Silva, J. F. G., Lencastre, M., & Castro, J. (2024). Modelagem Conceitual de Dívida Técnica na Engenharia de Requisitos. In 25a Workshop em Engenharia de Requisitos (WER 24).
Veizaga, A., Shin, S. Y., & Briand, L. C. (2024). Automated smell detection and recommendation in natural language requirements. IEEE Transactions on Software Engineering, 50(4), 695-720.
Wieringa, R. (2014). Design science methodology for information systems and software engineering. Springer-Verlag Berlin Heidelberg.
Publicado
25/05/2026
Como Citar
GUILHERMINO, Fernando; LENCASTRE, Maria.
Towards a Large Language Model Based Approach for the Management of Requirements Technical Debt. In: TRILHA DE NOVAS IDEIAS E RESULTADOS EMERGENTES EM SI - DESENHOS DE PESQUISA - SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 22. , 2026, Vitória/ES.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 178-184.
DOI: https://doi.org/10.5753/sbsi_estendido.2026.249035.
