| Title |
From requirements to executable tests: LLM-based system test generation for REST APIs |
| Authors |
Kochanovskis, Jaroslav ; Slotkienė, Asta |
| DOI |
10.15388/LMITT.2026.13 |
| Full Text |
|
| Is Part of |
Lietuvos magistrantų informatikos ir IT tyrimai: konferencijos darbai, 2026 m. gegužės 6 d. Vilnius.. Vilnius : Vilniaus universiteto leidykla. 2026, p. 118-130.. eISSN 2783-784X |
| Keywords [eng] |
software testing ; automated test generation ; natural language processing ; large language models ; system testing ; REST API |
| Abstract [eng] |
Modern software systems increasingly rely on APIs, making efficient testing essential for ensuring reliability and correctness. However, creating system tests from natural language requirements is typically a manual and time-consuming process. This research proposes an approach for automatically generating executable REST API tests from natural language requirements using large language models (LLMs) and OpenAPI specifications. A prototype system was developed and evaluated on two real-world APIs. The results show that the approach can generate executable pytest tests, achieve full endpoint reachability coverage, and provide stable automated test execution. |
| Published |
Vilnius : Vilniaus universiteto leidykla |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2026 |
| CC license |
|
