Dimensions in program synthesis

By M. Gyssens, J. Paredaens, D. V. Gucht, George H. L. Fletcher. 2010

170 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Software, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Software

In Code Generation & Program Synthesis

Citations in the corpus

Neural GPUs Learn Algorithms (2015, methodology): “It is known under names such as program synthesis, program induction, automatic programming, or inductive synthesis, and has a long history with many works that we do not cover here; see, e.g., Gulwani (2010) and Kitzelmann (2010) for a more general perspective.”
Neural Program Synthesis with Priority Queue Training (2018, background): “These techniques have found many important applications in practice, ranging from education to programming assistance (Gulwani, 2010).”
Synthesis of loop-free programs (2011, background): “We focus on the component-based synthesis problem where the goal is to build a system by composing base components.”
Toward Semantic Foundations for Program Editors (2017, background): “Indeed, suggestion generation is closely related to several major research areas: code completion [32, 18], program synthesis [17], and program repair [24, 31, 25, 22].”
A Survey on Large Language Models for Code Generation (2024, unknown): “The accessibility, effectiveness, and efficiency of using LLMs in daily tasks show the huge potential of applying LLMs in automatic code generation.”
On End-to-End Program Generation from User Intention by Deep Neural Networks (2015, background): “Such scenario of automatic program generation has long been the dream of software engineering (SE), and is closely related to a variety of SE tasks, e.g., algorithm discovery, programming assistance [6].”
FlashMeta: a framework for inductive program synthesis (2015, methodology): “Program synthesis is the task of synthesizing a program in an underlying programming language, given the user’s intent in the form of some speciﬁcation [6].”
GitHub Copilot AI pair programmer: Asset or Liability? (2022, background): “Program synthesis is useful for different purposes such as teaching, programmer assistance or the discovery of new algorithmic solutions for a problem [17].”
NLyze: interactive programming by natural language for spreadsheet data analysis and manipulation (2014, methodology): “Program synthesis is the task of automatically synthesizing a program in some underlying domain-speciﬁc language from a given speciﬁcation using some search technique [6].”
Code completion with statistical language models (2014, background): “For a broader survey in recent program synthesis techniques, see Gulwani [14].”
Learning to Solve Complex Tasks by Talking to Agents (2021, background): “Program Synthesis has traditionally focused on constructing executable programs from high-level speciﬁcations (Manna and Waldinger, 1980) or intentions given input-output examples (Gulwani, 2011) and other pieces of evidence including nat-ural language (Desai et al., 2016) (see Gulwani (2010)).”
Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language (2022, background): “The impact on educational practice of such technologies is unknown, with arguments on both sides—highlighting concerns of over-reliance by novices [6], and suggesting that the ability to synthesize code automatically could play a revolutionary role in teaching [11].”
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs (2018, methodology): “To solve this problem, we combine recent advances in program induction ( 31–37 ) along with the architectural advantages of VCC.”
Counterexample-Driven Genetic Programming: Heuristic Program Synthesis from Formal Specifications (2018, background): “how should user intent (Gulwani, 2010) be expressed? It is clear that tests and specifications are just the extremes of a conceivably rich spectrum.”