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

2026-04-23

AI Summary

This work addresses the limitations of existing large language model (LLM)-based approaches for unit test generation in Java projects characterized by complex inter-class dependencies, deep call chains, and intricate object initialization requirements. To overcome these challenges, the authors propose CAT, a novel method that systematically integrates static analysis–derived call chains and dependency context into LLM prompts. CAT constructs executable test templates incorporating method call relationships, constructor invocations, and third-party dependencies, and further refines failing test cases through an iterative repair mechanism. Experimental results on Defects4J demonstrate that CAT outperforms the state-of-the-art PANTA method, achieving relative improvements of 18.04% in line coverage and 21.74% in branch coverage, while consistently maintaining superior performance on real-world GitHub projects.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• test generation
• call chain
• dependency context
• LLM
• unit testing

Innovation

• call-chain-aware
• LLM-based test generation
• static analysis
• dependency context
• unit test synthesis