Reproduce “Large Language Models for Unit Test Generation: Achievements, Challenges, and Opportunities” 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
Bei Chu, Yang Feng, Kui Liu, Zhaoqiang Guo, Yichi Zhang, Hange Shi, Zifan Nan, Baowen Xu
The authors review 178 publications on large language model unit-test generation, tracing how project context supports construction and how build and execution feedback guides validation or repair. They frame these stages as a flexible lifecycle, not a fixed pipeline. On Defects4J, TestART’s pass rate was 78.55% versus 60.05% for ChatUniTest, but passing does not establish fault detection or oracle correctness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.