Reproduce “Learning Syntactic Program Transformations from Examples” 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
Reudismam Rolim, Gustavo Soares, Loris D'Antoni, Oleksandr Polozov, Sumit Gulwani, Rohit Gheyi, Ryo Suzuki, Bjoern Hartmann
REFAZER learns reusable program-editing rules from before-and-after code examples. It represents edits as syntax-tree rewrite rules and ranks candidates that fit the examples. In evaluations, it fixed 87% of student solutions in a same-assignment batch setting and synthesized intended transformations in 49/59 C# scenarios. These results depend on task-specific examples and tests and do not guarantee semantic correctness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.