alphaevolve

Open-source implementation of AlphaEvolve

A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use

CodeEvolve is an open-source evolutionary coding agent for algorithm discovery and optimization.

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

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

[ICLR26] AI-based scaling law discovery

PromptPotter: AI optimization engine for automated prompt engineering (APE). Searches and tunes prompts and parameters against your data using a generate-evaluate-critique cycle. Improve AI outputs, automate prompt optimization, and fine-tune your pipeline.

A Python library for evolving code and algorithms using Large Language Models (LLMs)

Executable benchmark for AI-driven potential discovery for the k-server conjecture, with evaluators, metric instances, and released experiment workflows.

Evolutionary agent for large codebases, built on top of git

Companion page for "Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery." A curated four-axis index covering MWPs, LLMs and reasoning models, multimodal geometry, Lean theorem proving, and verified discovery (FunSearch, AlphaEvolve, Erdős problems).

AI evolves trading strategies, then they sit an exam they can't cheat. AlphaEvolve-style search with sealed holdouts and a 7-market world exam.

An open-source AlphaEvolve-style evolutionary algorithm discovery engine. LLM-driven mutation operator inside an island-model evolutionary loop.

Genetics for Algorithm Discovery. Evolve ideas, not programs: every LLM idea becomes a named switch, and knockouts measure what each is worth. New lower bounds at 17 sizes of Tao et al.'s problem 60. Built at the London AI x Science Hackathon 2026.

Codex Skill and platform-neutral research CLI for reproducible, auditable OpenEvolve algorithm discovery with holdouts, ablations, budgets, and novelty audits.

Dream-RSI recursive self-improvement as a DeepSeek Harness plugin: discovery history becomes a replay simulator; candidate exploration policies are dream-evaluated off-policy and redeployed under a no-regression guarantee.

Independent exact certification of machine-generated mathematics — exact arithmetic, no code shared with the claimant, refusal as a verdict.

A transparent, recoverable, zero-runtime-dependency LLM program evolution kernel.

Using LLMs(not RL) to find new solutions for any hard problems.