High-Performance Symbolic Regression in Python and Julia

Physical Symbolic Optimization

Genetic Programming in Python, with a scikit-learn inspired API

Generating sets of formulaic alpha (predictive) stock factors via reinforcement learning.

A framework for gene expression programming (an evolutionary algorithm) in Python

A GPU-accelerated library for Tree-based Genetic Programming, leveraging PyTorch and custom CUDA kernels for high-performance evolutionary computation. It supports symbolic regression, classification, and policy optimization with advanced features like multi-output trees and benchmark tools.

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

EC-KitY: A scikit-learn-compatible Python tool kit for doing evolutionary computation.

[ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs

a python 3 library based on deap providing abstraction layers for symbolic regression problems.

[NeurIPS 2023] This is the official code for the paper "TPSR: Transformer-based Planning for Symbolic Regression"

Official repository for the paper "Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery"

Automatic parametric modeling with symbolic regression

[ICLR 2024 Spotlight] This is the official code for the paper "SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training"

predicting equations from raw data with deep learning

Symbolic regression is the task of identifying a mathematical expression that best fits a provided dataset of input and output values. In this work, we present SymbolicGPT, a novel transformer-based language model for symbolic regression.

[DMLR] Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discovery

Cartesian genetic programming (CGP) in pure Python.

A baseline implementation of genetic programming (using trees to encode programs) with some examples of usage.

AI Physicist, a paradigm with algorithms for learning theories from data, by Wu and Tegmark (2019)