PromptsApr 6, 2026·2 min read

AI Scientist — Automated Research Paper Generation

Fully automated AI system that conducts research, runs experiments, and writes complete scientific papers. Generates novel ideas, implements them, and produces LaTeX manuscripts. 12,000+ stars.

PR
Prompt Lab · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

git clone https://github.com/SakanaAI/AI-Scientist.git
cd AI-Scientist
pip install -r requirements.txt
# Run the full pipeline
python launch_scientist.py \
  --model claude-sonnet-4-20250514 \
  --experiment nanoGPT \
  --num-ideas 5

The system generates ideas, runs experiments, analyzes results, and writes a complete paper.


Intro

AI Scientist is a fully automated research system by Sakana AI that generates novel ideas, designs experiments, runs code, analyzes results, and writes complete scientific papers in LaTeX with 12,000+ GitHub stars. Given a research template and compute budget, it autonomously produces publishable-quality manuscripts — including literature review, methodology, results, and discussion sections. Best for researchers exploring AI-assisted scientific discovery and anyone curious about the frontier of automated research. Works with: Claude, GPT-4, Gemini. Setup time: under 10 minutes.


How It Works

1. Idea Generation

The system brainstorms novel research directions:

Input: "Improve training efficiency of small language models"
Generated Ideas:
1. Adaptive learning rate scheduling based on gradient noise
2. Curriculum learning with dynamic difficulty assessment
3. Sparse attention patterns for resource-constrained training
...

2. Experiment Design

For each idea, it designs and implements experiments:

# AI generates experiment code automatically
# Modifies the template codebase
# Adds metrics, logging, and ablation studies

3. Experiment Execution

Runs experiments with full logging:

Running experiment: adaptive_lr_scheduling
Epoch 1/50: loss=2.34, lr=0.001
Epoch 2/50: loss=1.89, lr=0.0008
...
Results: 15% improvement over baseline

4. Paper Writing

Generates a complete LaTeX paper:

├── paper.tex          # Full manuscript
├── figures/           # Generated plots
├── references.bib     # Cited works
└── review.txt         # Self-review and scoring

5. Self-Review

The system reviews its own paper and provides a score:

Novelty: 7/10
Significance: 6/10
Clarity: 8/10
Overall: Accept with minor revisions

Research Templates Available

Template Domain Description
nanoGPT NLP Small language model training
grokking ML Theory Generalization phenomena
2d_diffusion Generative AI 2D diffusion models

Key Stats

  • 12,000+ GitHub stars
  • By Sakana AI
  • End-to-end automated research
  • LaTeX paper generation
  • Self-review and scoring
  • Multiple research templates

FAQ

Q: What is AI Scientist? A: AI Scientist is an automated research system that generates ideas, runs experiments, and writes complete scientific papers autonomously using LLMs.

Q: Is AI Scientist free? A: Yes, open-source under Apache 2.0. You need LLM API keys and compute for experiments.

Q: Can AI Scientist produce publishable papers? A: It generates papers at workshop-quality level. The system includes self-review, but human review is recommended before submission.


🙏

Source & Thanks

Created by Sakana AI. Licensed under Apache 2.0.

AI-Scientist — ⭐ 12,000+

Thanks to Sakana AI for pushing the boundary of automated scientific discovery.

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets