2 papers
cs.CR2026
Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair
Wenji Bai, Muhammad Waseem, Zeeshan Rasheed +2
Localizing where an LLM-based agent first fails to uphold security during a repair can show which stage of its workflow needs an additional safeguard. This is difficult for silent…
cs.SE2026
When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems
Wenji Bai, Muhammad Waseem, Zeeshan Rasheed +2
LLM-based agents for automated code repair have received significant attention in recent years from both research and software engineering practice perspectives. However, limited a…