EvoGPT: Enhancing Test Suite Robustness via LLM-Based Generation and Genetic Optimization
This work addresses the need for more effective automated test generation in software engineering, though it is incremental as it builds on existing LLM and evolutionary methods.
The paper tackled the problem of generating robust unit tests by introducing EvoGPT, a hybrid framework combining LLM-based generation with evolutionary optimization, resulting in an average 10% improvement in code coverage and mutation score compared to baselines.
Large Language Models (LLMs) have recently emerged as promising tools for automated unit test generation. We introduce a hybrid framework called EvoGPT that integrates LLM-based test generation with evolutionary search techniques to create diverse, fault-revealing unit tests. Unit tests are initially generated with diverse temperature sampling to maximize behavioral and test suite diversity, followed by a generation-repair loop and coverage-guided assertion enhancement. The resulting test suites are evolved using genetic algorithms, guided by a fitness function prioritizing mutation score over traditional coverage metrics. This design emphasizes the primary objective of unit testing-fault detection. Evaluated on multiple open-source Java projects, EvoGPT achieves an average improvement of 10% in both code coverage and mutation score compared to LLMs and traditional search-based software testing baselines. These results demonstrate that combining LLM-driven diversity, targeted repair, and evolutionary optimization produces more effective and resilient test suites.