EUVIMEDEUVIMED entdecken
Crossref

G enesys : A Novel Evolutionary Program Synthesis Tool with Continuous Optimization

Shantanu Mandal, Todd Anderson, Javier Turek, Justin Gottschlich, Abdullah Muzahid

ACM Transactions on Probabilistic Machine Learning · 31.03.2026 · 2 (1) · 1-27

DOI: 10.1145/3776736 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Probabilistic Machine Learning, online erschienen am 12.02.2026. Verfasst von Shantanu Mandal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • NSF

Zitieren

APA

Mandal, S., Anderson, T., Turek, J., Gottschlich, J., & Muzahid, A. (2026). G enesys : A Novel Evolutionary Program Synthesis Tool with Continuous Optimization. ACM Transactions on Probabilistic Machine Learning, 2(1), 1-27. https://doi.org/10.1145/3776736

Vancouver

Mandal S, Anderson T, Turek J, Gottschlich J, Muzahid A. G enesys : A Novel Evolutionary Program Synthesis Tool with Continuous Optimization. ACM Transactions on Probabilistic Machine Learning. 2026;2(1):1-27. doi:10.1145/3776736

BibTeX
@article{Mandal2026,
  author = {Mandal, Shantanu and Anderson, Todd and Turek, Javier and Gottschlich, Justin and Muzahid, Abdullah},
  title = {G enesys : A Novel Evolutionary Program Synthesis Tool with Continuous Optimization},
  journal = {ACM Transactions on Probabilistic Machine Learning},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {1--27},
  doi = {10.1145/3776736}
}
Kostenlos starten →