# Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis

arXiv: https://arxiv.org/abs/2007.08095 · HTML: https://mlsanity.com/paper/2007.08095/

## Key facts

- Cited by 39 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 30 of 39)

- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Large Language Models as Analogical Reasoners](https://mlsanity.com/paper/2310.01714/) (2023)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [CURE: Code-Aware Neural Machine Translation for Automatic Program Repair](https://mlsanity.com/paper/2103.00073/) (2021)
- [NExT: Teaching Large Language Models to Reason about Code Execution](https://mlsanity.com/paper/2404.14662/) (2024)
- [From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging](https://mlsanity.com/paper/2410.01215/) (2024)
- [SelfEvolve: A Code Evolution Framework via Large Language Models](https://mlsanity.com/paper/2306.02907/) (2023)
- [Latent Execution for Neural Program Synthesis](https://mlsanity.com/paper/2107.00101/) (2021)
- [Fully Autonomous Programming with Large Language Models](https://mlsanity.com/paper/2304.10423/) (2023)
- [Tensor Program Optimization with Probabilistic Programs](https://mlsanity.com/paper/2205.13603/) (2022)
- [Is Programming by Example solved by LLMs?](https://mlsanity.com/paper/2406.08316/) (2024)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback](https://mlsanity.com/paper/2311.07215/) (2023)
- [Neural Task Synthesis for Visual Programming](https://mlsanity.com/paper/2305.18342/) (2023)
- [Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search](https://mlsanity.com/paper/2405.16450/) (2024)
- [RunBugRun -- An Executable Dataset for Automated Program Repair](https://mlsanity.com/paper/2304.01102/) (2023)
- [Learning to Combine Per-Example Solutions for Neural Program Synthesis](https://mlsanity.com/paper/2106.07175/) (2021)
- [Transcribing Natural Languages for The Deaf via Neural Editing Programs](https://mlsanity.com/paper/2112.09600/) (2021)
- [Learning to Edit Visual Programs with Self-Supervision](https://mlsanity.com/paper/2406.02383/) (2024)
- [Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods](https://mlsanity.com/paper/2406.15540/) (2024)
- [ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.02330/) (2025)
- [ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning](https://mlsanity.com/paper/2603.05863/) (2026)
- [Learning to Combine Instructions in LLVM Compiler](https://mlsanity.com/paper/2202.12379/) (2022)
- [NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging](https://mlsanity.com/paper/2505.15356/) (2025)
- [A Survey on Natural Language Processing for Programming](https://mlsanity.com/paper/2212.05773/) (2022)
- [Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models](https://mlsanity.com/paper/2503.07693/) (2025)

## Abstract (arXiv)

The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it still remains a challenge to synthesize programs that are consistent with the specification. In this work, we propose SED, a neural program generation framework that incorporates synthesis, execution, and debugging stages. Instead of purely relying on the neural program synthesizer to generate the final program, SED first produces initial programs using the neural program synthesizer component, then utilizes a neural program debugger to iteratively repair the generated programs. The integration of the debugger component enables SED to modify the programs based on the execution results and specification, which resembles the coding process of human programmers. On Karel, a challenging input-output program synthesis benchmark, SED reduces the error rate of the neural program synthesizer itself by a considerable margin, and outperforms the standard beam search for decoding.