Author

Zhijie Wang

View on Semantic Scholar

1 paper indexed here

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

Rethinking Code Performance Benchmarks for LLMs

An LLM-based multi-agent framework to generate performance-oriented tests that expose runtime differences more effectively than the original tests is proposed, which uses three separate agents to generate, diagnose, and repair deterministic tests that preserve functional correctness while better exposing performance differences.

Nhat Minh Lê, Yisen Xu, Zhijie Wang et al. · arXiv.org · 0 citations