# LLM-Guided Compositional Program Synthesis

arXiv: https://arxiv.org/abs/2503.15540 · HTML: https://mlsanity.com/paper/2503.15540/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2025.

## Built on by (most cited first, 5 of 5)

- [SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data](https://mlsanity.com/paper/2505.20347/) (2025)
- [A Survey of Inductive Reasoning for Large Language Models](https://mlsanity.com/paper/2510.10182/) (2025)
- [Program Synthesis via Test-Time Transduction](https://mlsanity.com/paper/2509.17393/) (2025)
- [From I/O to Code with Discovery Agent](https://mlsanity.com/paper/2605.15334/) (2026)
- [From Benchmark Data To Applicable Program Repair: An Experience Report](https://mlsanity.com/paper/2508.16071/) (2025)

## Abstract (arXiv)

Program synthesis from input-output examples, also called programming by example (PBE), has had tremendous impact on automating end-user tasks. Large language models (LLMs) have the ability to solve PBE tasks by generating code in different target languages, but they can fail unpredictably. To recover for failure, most approaches, such as self-reflection, use the LLM to solve the same task, but with a richer context. We introduce a novel technique that recovers from failure by constructing simpler subtasks for the LLM to solve. Our approach performs compositional program synthesis using LLMs, where LLM not only guides the decomposition of the PBE task into subtasks, but also solves the subtasks. We present different strategies for decomposing the original task. We experimentally show that our approach can solve challenging task instances that are not solved by self-reflection alone.