# Neural Program Search: Solving Programming Tasks from Description and Examples

arXiv: https://arxiv.org/abs/1802.04335 · HTML: https://mlsanity.com/paper/1802.04335/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2018.

## Built on by (most cited first, 10 of 10)

- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing](https://mlsanity.com/paper/2104.02443/) (2021)
- [CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay](https://mlsanity.com/paper/2402.04858/) (2024)
- [Explaining Competitive-Level Programming Solutions using LLMs](https://mlsanity.com/paper/2307.05337/) (2023)
- [Scaling Neural Program Synthesis with Distribution-based Search](https://mlsanity.com/paper/2110.12485/) (2021)
- [On Adversarial Robustness of Synthetic Code Generation](https://mlsanity.com/paper/2106.11629/) (2021)
- [Distilling Algorithmic Reasoning from LLMs via Explaining Solution Programs](https://mlsanity.com/paper/2404.08148/) (2024)
- [Amortizing Pragmatic Program Synthesis with Rankings](https://mlsanity.com/paper/2407.02499/) (2024)
- [WikiCoder: Learning to Write Knowledge-Powered Code](https://mlsanity.com/paper/2303.08574/) (2023)
- [Amortizing Pragmatic Program Synthesis with Rankings](https://mlsanity.com/paper/2309.03225/) (2023)

## Abstract (arXiv)

We present a Neural Program Search, an algorithm to generate programs from natural language description and a small number of input/output examples. The algorithm combines methods from Deep Learning and Program Synthesis fields by designing rich domain-specific language (DSL) and defining efficient search algorithm guided by a Seq2Tree model on it. To evaluate the quality of the approach we also present a semi-synthetic dataset of descriptions with test examples and corresponding programs. We show that our algorithm significantly outperforms a sequence-to-sequence model with attention baseline.