Resources

Curated collection of research papers, guides, tools, and community resources for AI-driven algorithm discovery and automated reasoning.

Publications & Articles

ARTICLE2025

OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve

Harnessing LLMs for Evolutionary Algorithm Discovery - A comprehensive implementation guide and exploration of using large language models to drive evolutionary algorithm discovery.

OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve
arXiv2025

ThetaEvolve: Test-time Learning on Open Problems

arXiv2025

CodeEvolve: An open source evolutionary coding agent for algorithm discovery and optimization

arXiv2025

ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution

arXiv2025

Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research

arXiv2026

AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization

Tools & Frameworks

Framework

ThetaEvolve: Test-time Learning on Open Problems

ThetaEvolve: Test-time Learning on Open Problems, enabling RL training on AlphaEvolve/OpenEvolve and emphasizing scaling test-time compute.

134
Python
Framework

OpenEvolve

Turn your LLMs into autonomous code optimizers that discover breakthrough algorithms. From random search to state-of-the-art: Watch your code evolve in real-time.

genetic-algorithmdiscovery evolutionary-algorithms
5.6k
Python
Framework

CodeEvolve

An open-source framework that combines large language models with evolutionary algorithms to discover and optimize high-performing code solutions.

genetic-algorithmevolutionary-algorithmscoding-agents
63
Python
Framework

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution

Shinka is a framework that combines Large Language Models (LLMs) with evolutionary algorithms to drive scientific discovery.

886
Python
Framework

DeepEvolve

DeepEvolve is a research and coding agent for new algorithm discovery in different science domains.

coding-agent llmmulti-agent
124
Python
Framework

SkyDiscover

SkyDiscover is a modular framework for AI-driven scientific and algorithmic discovery, providing a unified interface for implementing, running, and fairly comparing discovery algorithms across 200+ optimization tasks.

246
Python