A Qualitative and Quantitative Exploration of LLM-Based Test Generation Repair Loops
Large Language Model (LLM) pipelines can generate semantically meaningful unit tests with high coverage, but generated tests often fail to compile or execute. Many frameworks therefore use LLM-driven repair loops that iteratively re-prompt on failures until validation succeeds, but these repairs can introduce issues such as hallucinating an invented class solely to make the test pass. In this paper, we study repair-induced issues and effects of prompt strategy across three Java projects. We build a dataset of LLM-generated broken-to-fixed test pairs, where initially failing tests are repaired via a loop under zero-shot, few-shot, and chain-of-thought prompting, derive a taxonomy from 117 manually analyzed pairs (three anti-pattern categories, seven scenarios), and compare the performance of prompting strategies through repair rate and post-repair coverage.