Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/ai-scientist-v2-guide
Automated scientific discovery via agentic tree search by Sakana AI
Passed 19 of 23 test cases with the skill, and 11 of 23 without it.
and 11 more in the full report
8 fixed11 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Once a PaperWriter instance has generated the manuscript object in Python, what method call compiles the LaTeX source directly into a PDF file at a target path?
| Checked | Without skill | With skill |
|---|---|---|
| Calls the compile_latex method on the paper object. | Missed | Passed |
The instructions your model reads when the skill loads.
AI-Scientist-v2 is an open-source system developed by Sakana AI with over 2,000 GitHub stars that automates the full scientific research pipeline -- from idea generation through experimentation to paper writing. Building on the original AI Scientist, version 2 introduces an agentic tree search approach that systematically explores the space of research ideas, designs and runs experiments, analyzes results, and produces workshop-level scientific papers with minimal human intervention.
The key innovation in v2 is the tree search mechanism. Rather than pursuing a single research direction linearly, the system maintains a tree of possible research trajectories. At each node, the agent can branch into multiple experimental variations, evaluate the results, and prune unpromising directions while doubling down on successful ones. This mirrors how experienced researchers navigate the research landscape -- exploring broadly at first, then focusing resources on the most promising leads.
AI-Scientist-v2 has demonstrated the ability to generate novel, valid research papers in machine learning subfields including diffusion models, language model training, and optimization. While the generated papers are currently at workshop acceptance level, the system represents a significant step toward autonomous scientific discovery and is an invaluable tool for researchers looking to automate the more mechanical aspects of their research workflow.
# Clone the repository
git clone https://github.com/SakanaAI/AI-Scientist-v2.git
cd AI-Scientist-v2
# Create a conda environment
conda create -n ai-scientist python=3.11
conda activate ai-scientist
# Install dependencies
pip install -r requirements.txt
AI-Scientist-v2 requires several components:
# LLM API access (required for ideation, analysis, and writing)
export OPENAI_API_KEY=$OPENAI_API_KEY
# Or Anthropic
export ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY
# GPU access for running ML experiments
# Recommended: at least one NVIDIA GPU with 24GB+ VRAM
# LaTeX installation for paper compilation
# Ubuntu/Debian
test cases passed, vs 11 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.