The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Учёный ИИ: к полностью автоматизированному открытому научному поиску
2024-08-12
SCID: 54.1/mmynwmdb
Discuss with AI
AI Scientistautomated paper reviewautomated scientific discoverylarge language modelsopen-ended research
Figures from the paper
Abstract (AI)
One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aides to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific process. This paper presents the first comprehensive framework for fully automatic scientific discovery, enabling frontier large language models to perform research independently and communicate their findings. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its findings by writing a full scientific paper, and then runs a simulated review process for evaluation. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community. We demonstrate its versatility by applying it to three distinct subfields of machine learning: diffusion modeling, transformer-based language modeling, and learning dynamics. Each idea is implemented and developed into a full paper at a cost of less than $15 per paper. To evaluate the generated papers, we design and validate an automated reviewer, which we show achieves near-human performance in evaluating paper scores. The AI Scientist can produce papers that exceed the acceptance threshold at a top machine learning conference as judged by our automated reviewer. This approach signifies the beginning of a new era in scientific discovery in machine learning: bringing the transformative benefits of AI agents to the entire research process of AI itself, and taking us closer to a world where endless affordable creativity and innovation can be unleashed on the world's most challenging problems. Our code is open-sourced at https://github.com/SakanaAI/AI-Scientist
Key Findings
1
Some AI Scientist-generated papers exceeded the acceptance threshold of a top machine learning conference according to the automated reviewer.
2
The AI Scientist is presented as a comprehensive framework enabling frontier language models to conduct scientific research largely autonomously.
3
The authors designed and validated an automated reviewer that achieves near-human performance in evaluating scientific paper scores.
4
The framework was demonstrated across diffusion modeling, transformer-based language modeling, and learning dynamics, with each paper costing less than $15 to produce.
5
The system generates research ideas, writes and executes code, visualizes experiments, authors full scientific papers, and performs simulated peer review.
Research Object
The AI Scientist system (an autonomous framework using frontier large language models to generate research ideas, run experiments, write papers, and perform review)
Research Subject
The framework’s capability to autonomously perform the end-to-end research process and generate, evaluate, and communicate novel machine-learning research
Publication Details
Publication Date
2024-08-12
Journal
Publisher
ISSN
Cited by
1914
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
Highly accurate protein structure prediction with AlphaFold2021
PyTorch: An Imperative Style, High-Performance Deep Learning Library2019
Neural Machine Translation by Jointly Learning to Align and Translate2014
A survey on large language model based autonomous agents2024
GPT-4 Technical Report2023
Evaluating Large Language Models Trained on Code2021
An autonomous laboratory for the accelerated synthesis of inorganic materials2023
A Survey of Research on Cloud Robotics and Automation2015
Cited by15
A multi-agent system for automating scientific discovery2026
Agentic AI: a comprehensive survey of architectures, applications, and future directions2025
Accelerating scientific discovery with Co-Scientist2026
Towards end-to-end automation of AI research2026
DataSciBench: An LLM Agent Benchmark for Data Science2026
Evaluation and Benchmarking of LLM Agents: A Survey2025
Modular large language model agents for multi-task computational materials science2026
Beyond static responses: multi-agent LLM systems as a new paradigm for social science research2026
Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning2026
Autonomous artificial intelligence, scientific research, and human values2026
Large Language Model Agent for Modular Task Execution in Drug Discovery2026
The Hitchhiker’s Guide to Autonomous Research: A Survey of Scientific Agents2026
A Comparative Survey of Security Risks in AI Systems: From LLMs to AI Agents and Embodied Agents2026
OmicOS: A Comprehensive Omics Ecosystem Infrastructure and Agent System for the AI Era2026
HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discovery2025