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

April 20, 2026 ยท Grace Period ยท ๐Ÿ› Findings 2026

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Khang Tran, Khoa Nguyen, Cristian Borcea, NhatHai Phan arXiv ID 2604.17715 Category cs.SE: Software Engineering Cross-listed cs.LG Citations 0 Venue Findings 2026
Abstract
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. We propose GLMTest, the first program structure-aware LLM framework for targeted test case generation that seamlessly integrates code property graphs and code semantics using a graph neural network and a language model to condition test case generation on execution branches. This structured conditioning enables controllable and branch-targeted test case generation, thereby potentially enhancing bug and security risk discovery. Experiments on real-world projects show that GLMTest built on a Qwen2.5-Coder-7B-Instruct model improves branch accuracy from 27.4% to 50.2% on TestGenEval benchmark compared with state-of-the-art LLMs, i.e., Claude-Sonnet-4.5 and GPT-4o-mini.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Software Engineering