Another embodiment is directed to automatically resolving semantic errors in a software routine. A computer system provides the software routine with known inputs and corresponding expected outputs for portions of a program fragment where an error has been localized. The computer system learns a ...
to use a glass-box scoring function, given as a program itself that can be directly inspected. Glass-box optimization covers a wide range of problems, from computing the greatest common divisor of two integers, to learning-to-learn problems. In this paper, we present an intellige...
Program synthesis is the task of automatically discovering an executable piece of code given user intent expressed using various forms of constraints such as input-output examples, demonstrations, natural language, etc. Program synthesis has direct applications for various classes of users in the technol...
Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result in them making plausible but incorrect statements1,2. Thi...
The primary goal of program synthesis is to minimize human intervention in the coding process, reduce errors, and improve productivity. Program synthesis often involves the use of advanced algorithms, artificial intelligence, and machine learning techniques to search the space of possible programs that ...
In this work we introduce an alternative approach to guided program synthesis: instead of training a model ahead of time we show how to bootstrap one just in time, during synthesis, by learning from partial solutions encountered along the way. To make the best use of the model, we also ...
machine-learningsymbolic-executiondynamic-analysisprogram-verificationloop-invariantsinvariant-generationspecification-miningneural-network-verification UpdatedSep 5, 2024 Python Mondego/dafny-synthesis Star36 Code Issues Pull requests Towards AI-Assisted Synthesis of Verified Dafny Methods ...
We study machine learning formulations of inductive program synthesis; given input-output examples, we try to synthesize source code that maps inputs to corresponding outputs. Our aims are to develop new machine learning approaches based on neural networks and graphical models, and to understand the...
In particular, the space of all programs is infinitely large and lacks the local smoothness exploited by local optimization algorithms like gradient descent or Markov Chain Monte Carlo. We adopt a strategy based on constraint-based program synthesis, where the optimization problem is translated into ...
and transformed while establishing or maintaining important semantic properties. Scope In addition to the traditional PEPM topics (see below), PEPM 2025 welcomes submissions in new domains, in particular: Semantics based and machine-learning based program synthesis and program optimisation. Modeling, analy...