G enesys : A Novel Evolutionary Program Synthesis Tool with Continuous Optimization
Open Access
- 12 February 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Probabilistic Machine Learning
- Vol. 2 (1) , 1-27
Abstract
Automatic software generation based on some specification is known as program synthesis . Most existing approaches formulate program synthesis as a search problem with discrete parameters. In this article, we present a novel formulation of program synthesis as a continuous optimization problem using an evolutionary approach, known as Covariance Matrix Adaptation Evolution Strategy. We then propose several mapping schemes to convert the continuous formulation into actual programs and propose different restart policies for the evolutionary approach. This is the first work that demonstrates the feasibility of continuous approach in synthesizing complex programs, not just simple toy programs. We compare our system, Genesys , to several recent program synthesis techniques (in both discrete and continuous domains). We find that Genesys synthesizes more programs within a fixed time budget than those existing schemes. For example, for programs of length 10, Genesys synthesizes 28% more programs than those existing schemes within the same time budget.Keywords
Funding Information
- NSF (2301334)
This publication has 30 references indexed in Scilit:
- Generalized data structure synthesis2018
- Synthesis of Constraints for Mathematical Programming With One-Class Genetic ProgrammingIEEE Transactions on Evolutionary Computation, 2018
- Automatic Chemical Design Using a Data-Driven Continuous Representation of MoleculesACS Central Science, 2018
- Code completion with statistical language models2014
- Stochastic superoptimization2013
- Differential Evolution: A Survey of the State-of-the-ArtIEEE Transactions on Evolutionary Computation, 2010
- Smooth interpretation2010
- Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed2009
- ImageNet: A large-scale hierarchical image database2009
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991