![[2602.21997] Enhancing LLM-Based Test Generation by Eliminating Covered Code](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.21997] Enhancing LLM-Based Test Generation by Eliminating Covered Code
Summary
This paper presents a novel method for enhancing LLM-based unit test generation by eliminating covered code, addressing challenges in testing complex software methods.
Why It Matters
Automated test generation is crucial for software quality assurance. This research enhances the capabilities of LLMs in generating effective unit tests, potentially improving software reliability and reducing testing time, which is vital in today's fast-paced development environments.
Key Takeaways
- Proposes a scalable LLM-based unit test generation method.
- Utilizes context retrieval and iterative test generation to improve coverage.
- Demonstrates effectiveness through evaluations on open-source projects.
Computer Science > Software Engineering arXiv:2602.21997 (cs) [Submitted on 25 Feb 2026] Title:Enhancing LLM-Based Test Generation by Eliminating Covered Code Authors:WeiZhe Xu, Mengyu Liu, Fanxin Kong View a PDF of the paper titled Enhancing LLM-Based Test Generation by Eliminating Covered Code, by WeiZhe Xu and 2 other authors View PDF HTML (experimental) Abstract:Automated test generation is essential for software quality assurance, with coverage rate serving as a key metric to ensure thorough testing. Recent advancements in Large Language Models (LLMs) have shown promise in improving test generation, particularly in achieving higher coverage. However, while existing LLM-based test generation solutions perform well on small, isolated code snippets, they struggle when applied to complex methods under test. To address these issues, we propose a scalable LLM-based unit test generation method. Our approach consists of two key steps. The first step is context information retrieval, which uses both LLMs and static analysis to gather relevant contextual information associated with the complex methods under test. The second step, iterative test generation with code elimination, repeatedly generates unit tests for the code slice, tracks the achieved coverage, and selectively removes code segments that have already been covered. This process simplifies the testing task and mitigates issues arising from token limits or reduced reasoning effectiveness associated with excessively lo...