SakanaAI /AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
★ 14,997⑂ 2,089👁 167⑃ 80● 149▤ 0
TA的项目
+6
日增长
+60
周增长
+254
月增长
14,997
stars
2,089
forks
167
watchers
80
prs
149
issues
0
releases
README
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬 📚 [Paper] | 📝 [Blog Post] | 📂 [Drive Folder] One of the grand challenges of artificial intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used to aid human scientists—for example, for brainstorming ideas or writing code—they still require extensive manual supervision or are heavily constrained to specific tasks. We're excited to introduce The AI Scientist, the first comprehensive system for fully automatic scientific discovery, enabling Foundation Models such as Large Language Models (LLMs) to perform research independently. We provide all runs and data from our paper here, where we run each base model on each template for approximately 50 ideas. We highly recommend reading through some of the Claude papers to get a sense of the system's strengths and weaknesses. Here are some example papers generated by The AI Scientist 📝: 1. DualScale Diffusion: Adaptive Feature Balancing for Low-Dimensional Generative Models 2. Multi-scale Grid Noise Adaptation: Enhancing Diffusion Models For Low-dimensional Data 3. GAN-Enhanced Diffusion: Boosting Sample Quality and Diversity 4. DualDiff: Enhancing Mode Capture in Low-dimensional Diffusion Models via Dual-expert Denoising 5. StyleFusion: Adaptive Multi-style Generation in Character-Level Language Models 6. Adaptive Learning Rates for Transformers via Q-Learning 7. Unlocking Grokking: A Comparative Study of Weight Initialization Strategies in Transformer Models 8. Grokking Accelerated: Layer-wise Learning Rates for Transformer Generalization 9. Grokking Through Compression: Unveiling Sudden Generalization via Minimal Description Length 10. Accelerating Mathematical Insight: Boosting Grokking Through Strategic Data Augmentation Note: Caution! This codebase will execute LLM-written code. There are various risks and challenges associated with this autonomy, including the use of potentially dangerous packages, web access, and potential spawning of processes. Use at your own discretion. Please make sure to containerize and restrict web access appropriately. Table of Contents 1. Introduction 2. Requirements - Installation - Supported Models and API Keys 3. Setting Up the Templates - NanoGPT Template - 2D Diffusion Template - Grokking Template 4. Run AI Scientist Paper Generation Experiments 5. Getting an LLM-Generated Paper Review 6. Making Your Own Template - Community-Contributed Templates 7. Template Resources 8. Citing The AI Scientist 9. Frequently Asked Questions 10. Containerization Introduction We provide three templates, which were used in our paper, covering the following domains: NanoGPT, 2D Diffusion, and Grokking. These templates enable The AI Scientist to generate ideas and conduct experiments in these areas. We accept contributions of new templates from the community, but please
Top issues
#84https://www.semanticscholar.org/product/api#api-key-form", "code": "429"21 comments · 2024-08-30#104S2_API_KEY for semanticscholar.org 14 comments · 2024-09-05#78always backing off13 comments · 2024-08-28#92Deploy the large model locally12 comments · 2024-09-02#199[EPIC] AI Scientist 2 Issue cleanup11 comments · 2025-03-16#174After trying several times installing it I get constantly reload window and WSL breaks.11 comments · 2025-01-05#124AI - Scientist for Non-Developers11 comments · 2024-09-14#198calling AI scientists is overstatement10 comments · 2025-03-16
Discussions
#227Move to codeberg0 comments · 2025-09-28#206Peer Review0 comments · 2025-03-24#201Any plans on integrating with litellm or making openai API compatible llm connections ?0 comments · 2025-03-20#191`texlive-full` Package is broken0 comments · 2025-02-13#185How many Api`s needs AI-Scientist for full Funktion1 comments · 2025-01-31#170Borrowing data from OpenML (or HuggingFace and Kaggle)0 comments · 2024-12-24#169Can AI Scientist handle harvesting multiple GitHub repos for examples0 comments · 2024-12-24#168Paper Refinement Methods1 comments · 2024-12-24