Call-Chain-Aware LLM-Based Test Generation for Java Projects
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911619806658560 |
|---|---|
| author | Wang, Guancheng Xu, Qinghua Briand, Lionel C. Guo, Zhaoqiang Liu, Kui |
| author_facet | Wang, Guancheng Xu, Qinghua Briand, Lionel C. Guo, Zhaoqiang Liu, Kui |
| contents | Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to guide prompt construction, which is often insufficient for complex software systems with rich inter-class dependencies, deep call chains, and intricate object initialization requirements. In this paper, we present CAT, a novel call-chain-aware LLM-based test generation approach that explicitly incorporates call-chain and dependency contexts into prompts through dedicated static analysis. To construct executable, semantically valid test contexts, CAT systematically models caller--callee relationships, object constructors, and third-party dependencies, and supports iterative test fixing when generation failures occur. We evaluate CAT on the widely used Defects4J benchmark and on four real-world GitHub projects released after the LLM's cut-off date. The results show that, across projects in Defects4J, CAT improves line and branch coverage by 18.04% and 21.74%, respectively, over the state-of-the-art approach PANTA, while consistently achieving superior performance on post-cutoff real-world projects. An ablation study further demonstrates the importance of call-chain and dependency contexts in CAT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22046 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Call-Chain-Aware LLM-Based Test Generation for Java Projects Wang, Guancheng Xu, Qinghua Briand, Lionel C. Guo, Zhaoqiang Liu, Kui Software Engineering Artificial Intelligence Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution-path information to guide prompt construction, which is often insufficient for complex software systems with rich inter-class dependencies, deep call chains, and intricate object initialization requirements. In this paper, we present CAT, a novel call-chain-aware LLM-based test generation approach that explicitly incorporates call-chain and dependency contexts into prompts through dedicated static analysis. To construct executable, semantically valid test contexts, CAT systematically models caller--callee relationships, object constructors, and third-party dependencies, and supports iterative test fixing when generation failures occur. We evaluate CAT on the widely used Defects4J benchmark and on four real-world GitHub projects released after the LLM's cut-off date. The results show that, across projects in Defects4J, CAT improves line and branch coverage by 18.04% and 21.74%, respectively, over the state-of-the-art approach PANTA, while consistently achieving superior performance on post-cutoff real-world projects. An ablation study further demonstrates the importance of call-chain and dependency contexts in CAT. |
| title | Call-Chain-Aware LLM-Based Test Generation for Java Projects |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2604.22046 |