autoresearch
Andrej Karpathy's autonomous LLM research framework: AI agent runs overnight experiments on a real training setup, auto-editing code→5min training→evaluation in a loop, ~100 experiments per night on a single GPU
- Repository
- github.com/karpathy/autoresearch
Source attribution
- Awesome AI for Science — github.com/karpathy/autoresearch
Related resources
First system to make novel, verifiable scientific discoveries by pairing LLMs with evolutionary search, solving open problems in combinatorics (cap set problem) and discovering faster matrix multiplication algorithms
Automated and rigorous experiments using AI agents for scientific discovery
AI-human collaborative research platform where a human researcher works with a team of LLM agents via team and individual meetings to perform scientific research; demonstrated by designing new SARS-CoV-2 nanobodies with wet-lab validation
Extended autonomy AI scientist with 200 parallel agent rollouts, 42K lines of code execution, 1.5K papers analyzed per run, achieving 79.4% accuracy and 7 scientific discoveries (Edison Scientific)
Autonomous algorithm discovery combining evolutionary search with peer-review reward models, achieving best-known performance on circle packing problems
First system progressively surpassing human SOTA on frontier AI tasks (183.7%, 1.9%, 7.9% improvements), month-long autonomous discovery with 20,000+ GPU hours