DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914469299355648 |
|---|---|
| author | Han, Hojae Kim, Jaejin Hwang, Seung-won Kim, Yu Jin Lee, Moontae |
| author_facet | Han, Hojae Kim, Jaejin Hwang, Seung-won Kim, Yu Jin Lee, Moontae |
| contents | This work addresses test output prediction, a key challenge in test case generation. To improve the reliability of predicted outputs by LLMs, prior approaches generate code first to ground predictions. One grounding strategy is direct execution of generated code, but even minor errors can cause failures. To address this, we introduce LLM-based pseudocode execution, which grounds prediction on more error-resilient pseudocode and simulates execution via LLM reasoning. We further propose DuET, a dual-execution framework that combines both approaches by functional majority voting. Our analysis shows the two approaches are complementary in overcoming the limitations of direct execution suffering from code errors, and pseudocode reasoning from hallucination. On LiveCodeBench, DuET achieves the state-of-the-art performance, improving Pass@1 by 13.6 pp. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11514 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode Han, Hojae Kim, Jaejin Hwang, Seung-won Kim, Yu Jin Lee, Moontae Software Engineering Computation and Language This work addresses test output prediction, a key challenge in test case generation. To improve the reliability of predicted outputs by LLMs, prior approaches generate code first to ground predictions. One grounding strategy is direct execution of generated code, but even minor errors can cause failures. To address this, we introduce LLM-based pseudocode execution, which grounds prediction on more error-resilient pseudocode and simulates execution via LLM reasoning. We further propose DuET, a dual-execution framework that combines both approaches by functional majority voting. Our analysis shows the two approaches are complementary in overcoming the limitations of direct execution suffering from code errors, and pseudocode reasoning from hallucination. On LiveCodeBench, DuET achieves the state-of-the-art performance, improving Pass@1 by 13.6 pp. |
| title | DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode |
| topic | Software Engineering Computation and Language |
| url | https://arxiv.org/abs/2604.11514 |