# Neural Program Synthesis By Self-Learning

arXiv: https://arxiv.org/abs/1910.05865 · HTML: https://mlsanity.com/paper/1910.05865/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2019.

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

- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [Efficient Skill Discovery via Regret-Aware Optimization](https://mlsanity.com/paper/2506.21044/) (2025)
- [GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies](https://mlsanity.com/paper/2603.14245/) (2026)
- [Transformer Models for Type Inference in the Simply Typed Lambda Calculus: A Case Study in Deep Learning for Code](https://mlsanity.com/paper/2304.10500/) (2023)

## Abstract (arXiv)

Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssemblet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effective multi-entropy policy sampling technique to alleviate online update correlations. We apply AutoAssemblet to basic programming tasks and show significant higher success rates compared to several competing baselines.