CasModaTest: A Cascaded and Model-agnostic Self-directed Framework for Unit Test Generation

TL;DR

CasModaTest is a novel, model-agnostic framework that enhances unit test generation by combining cascaded stages for test prefix and oracle creation, significantly outperforming existing approaches in accuracy and coverage.

Contribution

It introduces a cascaded, end-to-end, model-agnostic approach for unit test generation, addressing limitations of existing ML-based methods with high-quality test prefix and oracle assembly.

Findings

Outperforms state-of-the-art methods by 60.62%-352.55% in accuracy.

Achieves 2.83%-87.27% higher focal method coverage.

Effective across different open-source LLMs.

Abstract

Though many machine learning (ML)-based unit testing generation approaches have been proposed and indeed achieved remarkable performance, they still have several limitations in effectiveness and practical usage. More precisely, existing ML-based approaches (1) generate partial content of a unit test, mainly focusing on test oracle generation; (2) mismatch the test prefix with the test oracle semantically; and (3) are highly bound with the close-sourced model, eventually damaging data security. We propose CasModaTest, a cascaded, model-agnostic, and end-to-end unit test generation framework, to alleviate the above limitations with two cascaded stages: test prefix generation and test oracle generation. Then, we manually build large-scale demo pools to provide CasModaTest with high-quality test prefixes and test oracles examples. Finally, CasModaTest automatically assembles the generated test prefixes and test oracles and compiles or executes them to check their effectiveness, optionally appending with several attempts to fix the errors occurring in compiling and executing phases. To evaluate the effectiveness of CasModaTest, we conduct large-scale experiments on a widely used dataset (Defects4J) and compare it with four state-of-the-art (SOTA) approaches by considering two performance measures. The experimental results indicate that CasModaTest outperforms all SOTAs with a substantial improvement (i.e., 60.62%-352.55% in terms of accuracy, 2.83%-87.27% in terms of focal method coverage). Besides, we also conduct experiments of CasModaTest on different open-source LLMs and find that CasModaTest can also achieve significant improvements over SOTAs (39.82%-293.96% and 9.25%-98.95% in terms of accuracy and focal method coverage, respectively) in end-to-end unit test generation