AI RESEARCH

Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics

arXiv CS.LG

ArXi:2604.17715v1 Announce Type: cross Recent advances in large language models for test case generation have improved branch coverage via prompt-engineered mutations. However, they still lack principled mechanisms for steering models toward specific high-risk execution branches, limiting their effectiveness for discovering subtle bugs and security vulnerabilities.