# Learning Fitness Functions for Machine Programming

arXiv: https://arxiv.org/abs/1908.08783 · HTML: https://mlsanity.com/paper/1908.08783/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2019.

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

- [Latent Execution for Neural Program Synthesis](https://mlsanity.com/paper/2107.00101/) (2021)
- [Large Language Models Based Automatic Synthesis of Software Specifications](https://mlsanity.com/paper/2304.09181/) (2023)
- [Toward Code Generation: A Survey and Lessons from Semantic Parsing](https://mlsanity.com/paper/2105.03317/) (2021)
- [Synthesizing Programs with Continuous Optimization](https://mlsanity.com/paper/2211.00828/) (2022)
- [Learning-Based Automatic Synthesis of Software Code and Configuration](https://mlsanity.com/paper/2305.15642/) (2023)

## Abstract (arXiv)

The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genetic algorithms have been used successfully for many problems, one criticism is that hand-crafting its fitness function, the test that aims to effectively guide its evolution, can be notably challenging. Our framework presents a novel approach to learn the fitness function using neural networks to predict values of ideal fitness functions. We also augment the evolutionary process with a minimally intrusive search heuristic. This heuristic improves the framework's ability to discover correct programs from ones that are approximately correct and does so with negligible computational overhead. We compare our approach with several state-of-the-art program synthesis methods and demonstrate that it finds more correct programs with fewer candidate program generations.