# DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode

arXiv: https://arxiv.org/abs/2604.11514 · HTML: https://mlsanity.com/paper/2604.11514/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules](https://mlsanity.com/paper/2310.08992/) (2023)
- [Interactive Code Generation via Test-Driven User-Intent Formalization](https://mlsanity.com/paper/2208.05950/) (2022)
- [No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping](https://mlsanity.com/paper/2509.21880/) (2025)
- [Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency](https://mlsanity.com/paper/2309.17272/) (2023)
- [CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation](https://mlsanity.com/paper/2308.08784/) (2023)
- [Large Language Models as Test Case Generators: Performance Evaluation and Enhancement](https://mlsanity.com/paper/2404.13340/) (2024)
- [CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing](https://mlsanity.com/paper/2403.13583/) (2024)
- [Semantic Scaffolds for Pseudocode-to-Code Generation](https://mlsanity.com/paper/2005.05927/) (2020)

## Abstract (arXiv)

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.