CLAIRE-Labo/EvoTune
Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
This framework helps machine learning researchers efficiently discover novel algorithms for complex computational problems like bin packing or the traveling salesman problem. It takes problem definitions and dataset examples as input, and outputs optimized Python algorithms ready for evaluation. The ideal user is a machine learning researcher or an optimization specialist looking to explore new algorithmic solutions beyond standard approaches.
130 stars.
Use this if you are a machine learning researcher who wants to automatically generate and optimize algorithms for challenging computational tasks using a combination of evolutionary search and large language models.
Not ideal if you are looking for a pre-built solution for a specific problem without exploring the underlying algorithm discovery process or if you do not have access to powerful GPU resources.
Stars
130
Forks
10
Language
Python
License
MIT
Category
Last pushed
Nov 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/CLAIRE-Labo/EvoTune"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
scientific-discovery/LLEMA
[ICLR 2026] LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery
flowersteam/LLM-Culture
Code for the "Cultural evolution in populations of Large Language Models" paper
OpenMLRL/LLM_Collab_Code_Generation
LLM Collaboration for Code Generation
papachristoumarios/llm-network-formation
Supplementary Code and Data for "Network Formation and Dynamics among Multi-LLMs"
chirindaopensource/bias_adjusted_LLM_agents_human_like_decision_making
End-to-End Python framework implementing bias-adjusted LLM agents for human-like decision-making...