Towards a Generative AI-Based Approach for End-to-End Test Automation

• Elvis Júnior UFF
• Vânia de Oliveira Neves UFF

DOI: https://doi.org/10.5753/cbsoft_estendido.2025.14173

Abstract

Software test automation is essential to ensure system quality; however, end-to-end (E2E) testing still faces challenges related to complexity and manual effort. This paper proposes GenIA-E2ETest, a Generative AI-based approach for the automatic generation of executable E2E test scripts from natural language descriptions. The approach was evaluated on two web applications and demonstrated promising results, achieving an average of 77% in element metrics, 85% in execution recall, and minimal manual adjustments (average of 10%). Despite limitations in highly dynamic flows, the results indicate that GenIA-E2ETest is effective in accelerating E2E test automation.

References

Caldiera, V. R. B. G. and Rombach, H. D. (1994). The goal question metric approach. Encyclopedia of software engineering, pages 528–532.

Hevner, A. R., March, S. T., Park, J., and Ram, S. (2004). Design science in information systems research. MIS quarterly, pages 75–105.

Junior, E., Valejo, A., Valverde-Rebaza, J. C., and Neves, V. O. (2025). Genia-e2etest: A generative ai-based approach for end-to-end test automation. In Proceedings of the XXXIX Brazilian Symposium on Software Engineering (SBES), Recife-PE, Brazil. To appear.