y0news
← Feed
Back to feed
🧠 AI🟢 BullishImportance 6/10

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair

arXiv – CS AI|Zhongqiang Pan, Chuanyi Li, Wenkang Zhong, Yi Feng, Bin Luo, Vincent Ng||7 views
🤖AI Summary

RepoRepair is a new AI-powered automated program repair system that uses hierarchical code documentation to fix bugs across entire software repositories. The system achieves a 45.7% repair rate on SWE-bench Lite at $0.44 per fix by leveraging LLMs like DeepSeek-V3 and Claude-4 for fault localization and code repair.

Key Takeaways
  • RepoRepair introduces a documentation-enhanced approach for repository-level automated program repair using LLMs
  • The system generates hierarchical code documentation to help LLMs understand repository-level context and dependencies
  • Achieves 45.7% repair rate on SWE-bench Lite at low cost of $0.44 per fix
  • Delivers state-of-the-art 37.1% repair rate on SWE-bench Multimodal benchmark
  • Combines DeepSeek-V3 for documentation generation with Claude-4 for actual code repairs
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles