CoEdPilot, an LLM-driven solution to recommend code edits by discriminating the relevant edits, exploring their interactive natures, and estimating its ripple effect in the project.
when a user finishes an edit with an optional editing description, CoEdPilot orchestrates multiple neural transformers to identify what and how to edit in the project regarding both edit location and edit content.
The datasets and models are available on Hugging Face
The code is available on GitHub
The VS Code extension is available on GitHub
More Details
Benchmark Construction
Statistics
Dataset link
GUI Introduction