AI models trained on GitHub pull requests show improved code editing

Researchers have developed a new method called Clean Pull Request (Clean-PR) to train AI models for repository-level code editing. This approach utilizes real-world GitHub pull requests, converting them into a structured dataset of over 2 million edits across 12 programming languages. By training models with this data, the researchers achieved significant performance improvements on the SWE-bench benchmark without relying on complex agent scaffolding during inference. AI

IMPACT Enhances AI's ability to perform complex, multi-file code modifications, potentially streamlining software development workflows.

RANK_REASON Academic paper detailing a new training methodology for AI code editing. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Clean Pull Request
• GitHub
• Qinglin Zhu
• SWE-bench

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →