Reproduce “LLM-Based Test Generation: Information Sources, Generation Strategies, and Quality Evidence” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni
The authors present a structured narrative synthesis of test generation, tracing generated artifacts, available behavior information, construction mechanisms, and evaluation evidence. It distinguishes executable tests from intermediate artifacts and separates operational measures such as execution and coverage from behavioral evidence about fault detection and acceptance of legal implementations. The curated register contains 95 records, but is not an exhaustive census.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.