VibeCheck: Assessing the Quality of LLM-Generated Unit Tests: A Multi-agent Empirical Study across Heterogeneous Repositories
Source
Anika Tabassum, Mushahid Intesum, Md. Fahim Arefin, Tarannum Shaila Zaman
Author
Anika Tabassum, Mushahid Intesum, Md. Fahim Arefin, Tarannum Shaila Zaman
Date
Why it matters
Comparing unit tests from Kiro, Antigravity, and Cursor (on Claude Sonnet 4.5) finds an execution-adequacy gap: generated tests usually run but frequently lack strong assertions and miss edge cases that coverage metrics hide.
articleFlowCheck: Helping End-Users Specify and Verify Intent in Vibe-Coded Web AppsReya Vir, Lydia Chilton, Zhuo Zhang, Eugene Wu
articleCode Health in LLM-Based Test Generation: Effectiveness and Token EfficiencyFreya Wirdemann, Markus Borg, Nadim Hagatulah, Adam Tornhill
articleVibe Coding: Practice, Performance, Productivity, and Risk -A State-of-the-Art ReviewDominik L. Michels, Mutaz Abu Ghazaleh, Francois Lazzari, Nabil Kassem, Jonathan Klein