AI patch refinement for higher-accuracy LLM-based code repair
This technology is a context-aware refinement module that transforms partially correct patches generated by large language models (LLM) into correct fixes, improving the accuracy of existing automatic program repair systems.
Unmet Need: Accurate and reliable LLM-based code repair
State-of-the-art LLM-based automated program repair (APR) tools generate code patches by reasoning over issue descriptions, codebases, and regression test suites. However, these tools frequently produce partially correct fixes that address individual instances of a bug while failing to resolve related cases or the underlying defect. As a result, many patches still require manual review and refinement before they can be safely merged, reducing the efficient gains of automated repair. Current APR systems lack systematic methods for refining these near-correct patches into complete, reliable fixes.
The Technology: Tool-agnostic refinement module for higher accuracy automated program repair
This technology is a software refinement module that transforms partially correct code patches generated by existing automatic program repair (APR) tools into complete and correct fixes. The module analyzes the issue description, draft patch, and surrounding code context to generate, evaluate, and integrate improved code edits before validating the final patch against the project’s test suite. Because the module refines the output of existing repair tools rather than replacing them, it can be integrated into both autonomous-agent and fixed-workflow APR systems.
This technology was evaluated on the SWE-Bench Lite and SWE-Bench Verified benchmarks of real-world GitHub issues. When integrated with five automated program repair tools, it improved bug-resolution rates by an average of approximately 14% and resolved several issues that none of the baseline tools were able to fix.
Applications:
- Plug-in enhancement layer for existing AI program-repair tools
- Automated resolution and quality-gating of AI-generated patches before merge
- Reduction of manual debugging and code-review effort in software maintenance
- Automated code review for security, reliability, and maintainability
- Large-scale legacy software modernization and re-architecting
- Benchmarking and research tool for studying automated patch correctness
Advantages:
- Plugs into existing repair tools instead of replacing them
- Boosts bug-resolution accuracy, fixing issues no other tool resolves
- Refines partially correct patches using issue and code context, cutting manual rework
- Tool-agnostic and broadly generalizable across repair systems
Lead Inventor:
Patent Information:
Patent Pending
Related Publications:
Tech Ventures Reference:
- Licensing Contact: Greg Maskel