Author

Shurui Zhou

h-index 0 View on Semantic Scholar

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests

A specification-based unit test generation paradigm that replaces the code under test in the prompt with an LLM-generated specification docstring is introduced, showing that this paradigm effectively reduces misguided tests while substantially increasing effective tests, improves multi-round, feedback-driven test generation pipelines, and remains applicable to both buggy and bug-free code.

Junda Zhao, Shurui Zhou, Eldan Cohen · arXiv.org · 0 citations

Jul 2026

Do Coverage and Mutation Scores of LLM-Generated Test Suites Correlate with Their Effectiveness? (Replicability Study)

It is found that the usefulness of coverage and mutation is highly context-dependent: in regression-style settings where the code provided to the LLM can be reasonably assumed bug-free, these metrics can provide meaningful signals when comparing across models; in another common scenario where the code-under-test may already be buggy and the goal is to expose the bug within the code-under-test, they no longer serve as reliable indicators.

Junda Zhao, Shurui Zhou, Eldan Cohen · arXiv.org · 0 citations