# ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis

arXiv: https://arxiv.org/abs/2307.13883 · HTML: https://mlsanity.com/paper/2307.13883/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 78 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [DeepCoder: Learning to Write Programs](https://mlsanity.com/paper/1611.01989/) (2016)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [Improving Text-to-SQL Evaluation Methodology](https://mlsanity.com/paper/1806.09029/) (2018)
- [RobustFill: Neural Program Learning under Noisy I/O](https://mlsanity.com/paper/1703.07469/) (2017)
- [The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers](https://mlsanity.com/paper/2108.12284/) (2021)
- [Learning to Execute](https://mlsanity.com/paper/1410.4615/) (2014)
- [Compositional generalization through meta sequence-to-sequence learning](https://mlsanity.com/paper/1906.05381/) (2019)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [Compositional Semantic Parsing with Large Language Models](https://mlsanity.com/paper/2209.15003/) (2022)
- [Write, Execute, Assess: Program Synthesis with a REPL](https://mlsanity.com/paper/1906.04604/) (2019)
- [Neuro-Symbolic Program Synthesis](https://mlsanity.com/paper/1611.01855/) (2016)
- [Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis](https://mlsanity.com/paper/1805.04276/) (2018)
- [Compositional Generalization via Neural-Symbolic Stack Machines](https://mlsanity.com/paper/2008.06662/) (2020)
- [Span-based Semantic Parsing for Compositional Generalization](https://mlsanity.com/paper/2009.06040/) (2020)
- [Making Transformers Solve Compositional Tasks](https://mlsanity.com/paper/2108.04378/) (2021)
- [Learning to Recombine and Resample Data for Compositional Generalization](https://mlsanity.com/paper/2010.03706/) (2020)

## Built on by (most cited first, 17 of 17)

- [NExT: Teaching Large Language Models to Reason about Code Execution](https://mlsanity.com/paper/2404.14662/) (2024)
- [Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM](https://mlsanity.com/paper/2403.19114/) (2024)
- [Is Programming by Example solved by LLMs?](https://mlsanity.com/paper/2406.08316/) (2024)
- [EVOR: Evolving Retrieval for Code Generation](https://mlsanity.com/paper/2402.12317/) (2024)
- [Case2Code: Scalable Synthetic Data for Code Generation](https://mlsanity.com/paper/2407.12504/) (2024)
- [FactorSim: Generative Simulation via Factorized Representation](https://mlsanity.com/paper/2409.17652/) (2024)
- [Gradient-Based Program Synthesis with Neurally Interpreted Languages](https://mlsanity.com/paper/2604.18907/) (2026)
- [Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction](https://mlsanity.com/paper/2501.16524/) (2025)
- [Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction](https://mlsanity.com/paper/2406.12725/) (2024)
- [Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model](https://mlsanity.com/paper/2503.08738/) (2025)
- [Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning](https://mlsanity.com/paper/2507.15877/) (2025)
- [Diverse In-Context Example Selection After Decomposing Programs and Aligned Utterances Improves Semantic Parsing](https://mlsanity.com/paper/2504.03541/) (2025)
- [Beyond Either-Or Reasoning: Transduction and Induction as Cooperative Problem-Solving Paradigms](https://mlsanity.com/paper/2505.14744/) (2025)
- [Compositional Models for Estimating Causal Effects](https://mlsanity.com/paper/2406.17714/) (2024)
- [A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition](https://mlsanity.com/paper/2505.02627/) (2025)
- [A Small-Scale System for Autoregressive Program Synthesis Enabling Controlled Experimentation](https://mlsanity.com/paper/2602.09112/) (2026)
- [Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer](https://mlsanity.com/paper/2608.03461/) (2026)

## Abstract (arXiv)

When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, we can measure whether they compositionally generalize, that is, whether a model that has been trained on the simpler subtasks is subsequently able to solve more complex tasks. In this paper, we characterize several different forms of compositional generalization that are desirable in program synthesis, forming a meta-benchmark which we use to create generalization tasks for two popular datasets, RobustFill and DeepCoder. We then propose ExeDec, a novel decomposition-based synthesis strategy that predicts execution subgoals to solve problems step-by-step informed by program execution at each step. When used with Transformer models trained from scratch, ExeDec has better synthesis performance and greatly improved compositional generalization ability compared to baselines. Finally, we use our benchmarks to demonstrate that LLMs struggle to compositionally generalize when asked to do programming-by-example in a few-shot setting, but an ExeDec-style prompting approach can improve the generalization ability and overall performance.