New CoHarden framework improves AI-driven bug fixing with iterative test hardening

Researchers have developed a new framework called CoHarden to improve the effectiveness of automated program repair (APR) using large language models (LLMs). The framework addresses limitations in existing bug reproduction tests (BRTs) by introducing the concept of 'lax' tests, which can incorrectly pass flawed patches. CoHarden iteratively refines both the test and the fix, ensuring that the generated test does not admit regressions, thereby enhancing repair success rates. Experiments on the SWE-bench Verified benchmark demonstrated that CoHarden significantly outperforms previous baselines in resolving bugs. AI

IMPACT Enhances AI's capability in software development by improving automated bug fixing and repair.

RANK_REASON The cluster contains a research paper detailing a new framework for automated program repair. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Automated program repair tool
• Bug reproduction tests
• CoHarden
• large-language models
• SWE-bench Verified

• paper
• product

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