BROWSE
Detail
Conference Paper
DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
- Authors
- Hojae Han, Jaejin Kim, Seung-won Hwang, Yu Jin Kim, Moontae Lee
- Issue Date
- 2026-07
- Citation
- Findings of the Association for Computational Linguistics: ACL 2026, pp.43221-43243
- Publisher
- Association for Computational Linguistics
- Language
- English
- Type
- Conference Paper
- Abstract
- 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. For filtering candidates in code generation, DUET shows the best Pass@1 on LiveCodeBenchEasy, BigCodeBench-Hard, DevEval and HumanEval(+).
- KSP Keywords
- Art performance, Dual Execution, Error-resilient, Execution Framework, Majority Voting(MV), Test case generation, code generation, output prediction, state-of-The-Art
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
