# Call-Chain-Aware LLM-Based Test Generation for Java Projects

arXiv: https://arxiv.org/abs/2604.22046 · HTML: https://mlsanity.com/paper/2604.22046/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018)
- [Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM](https://mlsanity.com/paper/2402.00097/) (2024)
- [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024)
- [LLM Test Generation via Iterative Hybrid Program Analysis](https://mlsanity.com/paper/2503.13580/) (2025)
- [Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis](https://mlsanity.com/paper/2412.14841/) (2024)
- [CITYWALK: Enhancing LLM-Based C++ Unit Test Generation via Project-Dependency Awareness and Language-Specific Knowledge](https://mlsanity.com/paper/2501.16155/) (2025)
- [Static Program Analysis Guided LLM Based Unit Test Generation](https://mlsanity.com/paper/2503.05394/) (2025)

## Abstract (arXiv)

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, and compare it with the state-of-the-art LLM-based approach PANTA and the search-based tool EvoSuite. The results show that, across projects in Defects4J, CAT improves line coverage, branch coverage, and mutation score by 12.52, 12.97, and 14.39 percentage points (18.02%, 21.52%, and 26.94% relative), respectively, over PANTA, and by 9.67, 4.17, and 15.70 percentage points (13.37%, 6.04%, and 30.13% relative) over EvoSuite. On the post-cutoff projects, CAT also achieves the highest average line coverage, branch coverage, and mutation score among all compared approaches. An ablation study further demonstrates the importance of call-chain and dependency contexts in CAT.