From Provable Correctness to Probabilistic Generation: A Comparative Review of Program Synthesis Paradigms
By: Zurabi Kobaladze, Anna Arnania, Tamar Sanikidze
Potential Business Impact:
Computers write code from simple instructions.
Program synthesis--the automated generation of executable code from high-level specifications--has been a central goal of computer science for over fifty years. This thesis provides a comparative literature review of the main paradigms that have shaped the field, tracing its evolution from formal logic based methods to recent advances using large scale neural models. We examine five key approaches: logic based (deductive) synthesis, inductive (example based) synthesis, sketch/schema based synthesis, large language model based synthesis, and neuro-symbolic hybrids. For each, we analyze foundational principles, notable systems, and practical applications, highlighting trade offs between correctness guarantees, specification requirements, search complexity, and expressive power. By reviewing developments from formally verified synthesis tools such as KIDS and Coq to data driven models generating probabilistic code from natural language like Codex, we present a comprehensive narrative of progress and ongoing challenges. This work emphasizes the transition from symbolic to hybrid neuro-symbolic methods and outlines future directions for reliable and scalable program synthesis.
Similar Papers
Towards a unified framework for programming paradigms: A systematic review of classification formalisms and methodological foundations
Programming Languages
Builds code styles from simple math pieces
On systematic construction of correct logic programs
Logic in Computer Science
Makes computer programs always give correct answers.
GPU accelerated program synthesis: Enumerate semantics, not syntax!
Programming Languages
Makes computers write code from examples faster.