Consistency Meets Verification: Enhancing Test Generation Quality in Large Language Models Without Ground-Truth Solutions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912896866320384 |
|---|---|
| author | Taherkhani, Hamed DaghighFarsoodeh, Alireza Chowdhury, Mohammad Pham, Hung Viet Hemmati, Hadi |
| author_facet | Taherkhani, Hamed DaghighFarsoodeh, Alireza Chowdhury, Mohammad Pham, Hung Viet Hemmati, Hadi |
| contents | Large Language Models (LLMs) have significantly advanced automated test generation, yet existing methods often rely on ground-truth code for verification, risking bug propagation and limiting applicability in test-driven development. We present ConVerTest, a novel two-stage pipeline for synthesizing reliable tests without requiring prior code implementations. ConVerTest integrates three core strategies: (i) Self-Consistency(SC) to generate convergent test cases via majority voting; (ii) Chain-of-Verification (CoVe) for iterative, reasoning-guided code refinement; and (iii) a Dual Execution Agreement to crossvalidate code and tests through consensus. Experiments on BIGCODEBENCH and LESS BASIC PYTHON PROBLEMS (LBPP) benchmarks demonstrate that ConVerTest improves test validity, line coverage, and mutation scores by up to 39%, 28%, and 18% respectively over baselines. Our findings highlight ConVerTest as a robust solution for mitigating hallucinations and enhancing the reliability of autonomous software testing agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10522 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Consistency Meets Verification: Enhancing Test Generation Quality in Large Language Models Without Ground-Truth Solutions Taherkhani, Hamed DaghighFarsoodeh, Alireza Chowdhury, Mohammad Pham, Hung Viet Hemmati, Hadi Software Engineering Large Language Models (LLMs) have significantly advanced automated test generation, yet existing methods often rely on ground-truth code for verification, risking bug propagation and limiting applicability in test-driven development. We present ConVerTest, a novel two-stage pipeline for synthesizing reliable tests without requiring prior code implementations. ConVerTest integrates three core strategies: (i) Self-Consistency(SC) to generate convergent test cases via majority voting; (ii) Chain-of-Verification (CoVe) for iterative, reasoning-guided code refinement; and (iii) a Dual Execution Agreement to crossvalidate code and tests through consensus. Experiments on BIGCODEBENCH and LESS BASIC PYTHON PROBLEMS (LBPP) benchmarks demonstrate that ConVerTest improves test validity, line coverage, and mutation scores by up to 39%, 28%, and 18% respectively over baselines. Our findings highlight ConVerTest as a robust solution for mitigating hallucinations and enhancing the reliability of autonomous software testing agents. |
| title | Consistency Meets Verification: Enhancing Test Generation Quality in Large Language Models Without Ground-Truth Solutions |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2602.10522 |