Code Building Genetic Programming

TL;DR

This paper introduces Code Building Genetic Programming (CBGP), a novel framework that synthesizes complex programs with arbitrary data types and structures, leveraging language features like reflection and first-class specifications.

Contribution

CBGP enables the synthesis of programs with complex data types and structures, surpassing limitations of previous genetic programming methods.

Findings

Successfully synthesized programs with non-primitive, polymorphic data types.

Produced programs that incorporate complex data structures from existing codebases.

Demonstrated capabilities on new and standard program synthesis benchmarks.

Abstract

In recent years the field of genetic programming has made significant advances towards automatic programming. Research and development of contemporary program synthesis methods, such as PushGP and Grammar Guided Genetic Programming, can produce programs that solve problems typically assigned in introductory academic settings. These problems focus on a narrow, predetermined set of simple data structures, basic control flow patterns, and primitive, non-overlapping data types (without, for example, inheritance or composite types). Few, if any, genetic programming methods for program synthesis have convincingly demonstrated the capability of synthesizing programs that use arbitrary data types, data structures, and specifications that are drawn from existing codebases. In this paper, we introduce Code Building Genetic Programming (CBGP) as a framework within which this can be done, by leveraging programming language features such as reflection and first-class specifications. CBGP produces a computational graph that can be executed or translated into source code of a host language. To demonstrate the novel capabilities of CBGP, we present results on new benchmarks that use non-primitive, polymorphic data types as well as some standard program synthesis benchmarks.