AlphaTensor (DeepMind, Nature 2022)
github.com/google-deepmind/alphatensorReinforcement learning agent that discovers provably correct and faster matrix multiplication algorithms via tensor decomposition games, finding a 47-multiplication algorithm for 4x4 matrices (improving on Strassen's 49 from 1969) and releasing 14,236+ nonequivalent discovered factorizations with GPU benchmarking scripts (Google DeepMind, 2.9K+ stars, Apache 2.0)
Sourced from
- Awesome AI for Science — github.com/google-deepmind/alphatensor
- GitHub — github.com/google-deepmind/alphatensor
Related resources
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
Lightweight Markdown-only skills for autonomous ML research with cross-model review loops, idea discovery, and experiment automation; no framework lock-in, works with Claude Code, Codex, OpenClaw, or any LLM agent (12.8K+ stars, MIT License, 2026)
Open-source LLM-powered R&D agent framework automating data-driven AI solution building through automated research, development, and evolution; achieves top open-source performance on MLE-Bench with dual Researcher-Developer agents and supports research copilot, data mining, Kaggle, and quant R&D workflows (13.6K+ stars, MIT License, 2025-2026)
Fully autonomous research from idea to paper with multi-agent debate, citation verification, and OpenClaw integration (11K+ stars, 2026)
First fully autonomous open-ended scientific discovery system with official implementation: hypothesis→experiment→writing→review simulation (13.8K+ stars, 2024)
Open-source implementation of AlphaEvolve's evolutionary coding agent paradigm, enabling LLMs to autonomously discover and optimize algorithms through iterative evolution, matching the approach behind DeepMind's breakthrough matrix multiplication discovery (6.2K+ stars, 2025)