AI RESEARCH
ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse
arXiv CS.CL
•
ArXi:2605.17450v1 Announce Type: cross Large language model (LLM) agents are increasingly used for automated vulnerability repair (AVR), where repository-level reasoning enables them to inspect context and produce source-code patches. However, recent empirical results show that these agents still struggle with real-world vulnerabilities. Their main failure mode is semantic misunderstanding: choosing a repair direction that does not match the root cause. We identify two reasons for this gap. Existing agents usually reason from the failing execution alone.