Reproduce “Keeping Fuzzers on Duty: Repairing Fuzzing Build Breakages in Continuous Open-Source Fuzzing” 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
Zhuang Zhao, Jiongchi Yu, Yao Zhang, Dongge Liu, Qiang Hu, Xiaohong Li, Yang Liu
FuzzMedic uses build logs and repository history to locate likely causes across project code and OSS-Fuzz configuration, then applies patches with repair guidance and recoverable build states. On a benchmark of 128 reproducible failures from 113 projects, it restored 62 builds (48.44%), versus 27 for CompileAgent; success required passing OSS-Fuzz check_build and does not establish semantic correctness or represent all OSS-Fuzz failures.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.