The Abstraction and Reasoning Corpus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

Using artificial intelligence and genetic algorithms to automatically write programs. Tutorial: http://www.primaryobjects.com/cms/article149

A Dataset of Python Challenges for AI Research

Microsoft Program Synthesis using Examples SDK is a framework of technologies for the automatic generation of programs from input-output examples. This repo includes samples and sample data for the Microsoft Program Synthesis using Example SDK.

Direct Manipulation Programming for HTML/SVG

multilspy is a lsp client library in Python intended to be used to build applications around language servers.

Performs string manipulation tasks by learning from the provided example(s), instead of having to program them out explicitly.

APPS: Automated Programming Progress Standard (NeurIPS 2021)

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

A relation-aware semantic parsing model from English to SQL

Code for Parsel 🐍 - generate complex programs with language models

Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.

discover elisp functions that do what you want

🌌️Fuzz4All: Universal Fuzzing with Large Language Models

Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.

An inductive logic programming system

A Python framework for program synthesis with a focus on Automated Machine Learning.

[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

Metagol - an inductive logic programming system