#Program-synthesis

Showing 13 of 13 repositories tagged #program-synthesis, ranked by stars

fchollet
fchollet
ARC-AGI

The Abstraction and Reasoning Corpus

Score
100
★ 4.8k ⑂ 719 +2/day
JavaScript
evalplus
evalplus
evalplus

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

Score
75
★ 1.8k ⑂ 201 +2/day
Python
primaryobjects
primaryobjects
AI-Programmer

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

Score
80
★ 1.1k ⑂ 263 +1/day
C#
microsoft
microsoft
PythonProgrammingPuzzles

A Dataset of Python Challenges for AI Research

Score
0
★ 999 ⑂ 96 +1/day
Python
microsoft
microsoft
multilspy

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

Score
100
★ 591 ⑂ 108 +1/day
Python
bigcode-project
bigcode-project
bigcodebench

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

Score
50
★ 513 ⑂ 74 +1/day
Python
microsoft
microsoft
monitors4codegen

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.

Score
40
★ 281 ⑂ 33
Python
Leeroo-AI
Leeroo-AI
kapso

A Knowledge-grounded framework for Autonomous ML/AI Program Synthesis and Optimization

Score
25
★ 93 ⑂ 8 +1/day
Python
google-research
google-research
plur

PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading the datasets. This is done by offering a unified API and data structures for all datasets.

Score
20
★ 90 ⑂ 17
Python
evo-eval
evo-eval
evoeval

EvoEval: Evolving Coding Benchmarks via LLM

Score
0
★ 84 ⑂ 13
Python
nerdimite
nerdimite
neuro-symbolic-ai-soc

Neuro-Symbolic Visual Question Answering on Sort-of-CLEVR using PyTorch

Score
0
★ 63 ⑂ 13 +1/day
Jupyter Notebook
google
google
ARC-GEN

A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus

Score
60
★ 50 ⑂ 10
Python
gaosu0715-lgtm
gaosu0715-lgtm
Evolutionary-Alpha-Miner

Family-aware evolutionary alpha mining with LLM-guided symbolic hybridization.

Score
0
★ 44 ⑂ 11
Related Topics
#artificial-intelligence#large-language-models#llm#ai#benchmark#chatgpt#gpt-4#code-generation#testing#genetic-programming#ai4code#code-analysis

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly