SakanaAI/AI-Scientist-v3

The Agentic Scientist Orchestrating Coding Agents for Automated Scientific (Co-)Discovery Turn a task description into experiments, ablations, and a paper, driven by coding agents. Agentic Scientist treats coding agents as AI scientists. Starting from a task.md, the agents propose ideas, run experiments, evaluate outcomes against the task rubric, and iterate toward stronger programs. The pipeline then runs baselines and ablations, a sealed final evaluation, post-hoc analyses, and writes the paper, with every stage kept under one run directory. The recommended setup runs every agent phase inside Docker, which is the default for agsci run. Install Docker, then build the agent image: If the build cannot reach package mirrors, add --network=host to the docker build command. .venv and installs the agsci command: OPENAIAPIKEY, GEMINIAPIKEY, ... whichever your agent needs). The pipeline mounts it into the agent containers. Never commit it. runs, install the CLI of the agent you use plus Git…