AI科学家：迈向全自动开放式科学发现
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
AI总结：
本文提出AI科学家框架，使大语言模型能自动完成从生成研究想法、编写代码、执行实验到撰写论文和模拟评审的全流程，并以低成本产出超过顶级会议接收阈值的论文，推动全自动开放式科学发现。
摘要：
人工通用智能的重大挑战之一是开发能够进行科学研究并发现新知识的智能体。尽管前沿模型已被用作人类科学家的辅助工具，例如用于头脑风暴构思、编写代码或预测任务，但它们仍然只执行科学过程的一小部分。本文提出了第一个用于全自动科学发现的综合框架，使前沿大语言模型能够独立进行研究并交流其发现。我们介绍了AI科学家（The AI Scientist），它能够生成新颖的研究想法、编写代码、执行实验、可视化结果、通过撰写完整科学论文来描述其发现，然后运行模拟评审过程进行评估。原则上，这一过程可以重复进行，以开放式的方式迭代发展想法，类似于人类科学界的行为方式。我们通过将其应用于机器学习的三个不同子领域来展示其多功能性：扩散建模、基于Transformer的语言建模和学习动力学。每个想法都被实现并发展为完整的论文，每篇论文的成本低于15美元。为了评估生成的论文，我们设计并验证了一个自动评审器，并证明其在评估论文评分方面达到了接近人类的性能。根据我们的自动评审器判断，AI科学家可以产出超过顶级机器学习会议接收阈值的论文。这一方法标志着机器学习领域科学发现新时代的开始：将AI智能体的变革性益处带入AI自身的整个研究过程，使我们更接近一个世界，在这个世界中，无穷无尽且负担得起的创造力和创新可以被释放到世界上最棘手的问题上。我们的代码已在 https://github.com/SakanaAI/AI-Scientist 开源。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
