Back to search

Article

When Generative AI Writes Test Cases: Scenario-Driven Evaluation of Generated Tests

2026-07-06

Abstract excerpt

<title>Abstract</title> <p> Software developers increasingly turn to Generative AI (GenAI) to generate unit tests. Moreover, they can interact with GenAI in different ways, e.g., directly prompting to generate a test suite or asking for higher-level test scenarios.However, we lack the means to compare the effectiveness of these strategies.Commonly used metrics, e.g., coverage or pass@k, give limited insight into...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
00b221fd-281b-5a51-bccc-296ef8e146e5
DOI
10.21203/rs.3.rs-9238547/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
When Generative AI Writes Test Cases: Scenario-Driven Evaluation of Generated TestsDOI 10.21203/rs.3.rs-9238547/v1
Select a neighboring publication to make it the new centre.