deep-symbolic-mathematics/LLM-SR
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models
This project helps scientists and researchers discover the underlying mathematical equations that govern their experimental data. You provide numerical observations from your experiments, and it outputs interpretable, accurate mathematical formulas. This is for anyone in scientific fields needing to model complex phenomena, such as physicists, biologists, or materials scientists.
216 stars. No commits in the last 6 months.
Use this if you have experimental data and want to automatically uncover the compact, explainable equations that describe the relationships within your observations, even for complex systems.
Not ideal if you already have a strong hypothesis for your equation's structure or if you primarily need to forecast outcomes without requiring an interpretable mathematical model.
Stars
216
Forks
44
Language
Python
License
MIT
Category
Last pushed
Jul 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/deep-symbolic-mathematics/LLM-SR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ExtensityAI/symbolicai
A neurosymbolic perspective on LLMs
TIGER-AI-Lab/MMLU-Pro
The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding...
microsoft/interwhen
A framework for verifiable reasoning with language models.
zhudotexe/fanoutqa
Companion code for FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language...
xlang-ai/Binder
[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"