AI科學家-v2：通過代理樹搜索實現工作坊級自動化科學發現

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

April 10, 2025

作者: Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shengran Hu, Chris Lu, Jakob Foerster, Jeff Clune, David Ha

cs.AI

摘要

AI正日益在变革科学发现方式中扮演着关键角色。我们推出The AI Scientist-v2，这是一个端到端的自主系统，能够生成首篇完全由AI创作并通过同行评审的工作坊论文。该系统能够迭代地提出科学假设、设计并执行实验、分析及可视化数据，并自主撰写科学手稿。相较于其前身（v1，Lu等人，2024年arXiv:2408.06292），The AI Scientist-v2消除了对人类编写代码模板的依赖，有效泛化至多种机器学习领域，并采用了一种由专用实验管理代理监督的新型渐进式自主树搜索方法。此外，我们通过整合视觉-语言模型（VLM）反馈循环，增强了AI审稿组件，以迭代优化内容与图表的美学效果。我们通过向ICLR工作坊提交三篇完全自主的手稿来评估The AI Scientist-v2。值得注意的是，其中一篇手稿得分之高，超过了人类平均接受门槛，标志着首篇完全由AI生成的论文成功通过同行评审。这一成就凸显了AI在全方位开展科学研究方面的日益增强的能力。我们预见，自主科学发现技术的进一步进步将深刻影响人类知识生成，使研究生产力达到前所未有的规模，并显著加速科学突破，极大地造福社会。我们已在https://github.com/SakanaAI/AI-Scientist-v2开源代码，以促进这一变革性技术的未来发展。我们还探讨了AI在科学中的角色，包括AI安全。

English

AI is increasingly playing a pivotal role in transforming how scientific discoveries are made. We introduce The AI Scientist-v2, an end-to-end agentic system capable of producing the first entirely AI generated peer-review-accepted workshop paper. This system iteratively formulates scientific hypotheses, designs and executes experiments, analyzes and visualizes data, and autonomously authors scientific manuscripts. Compared to its predecessor (v1, Lu et al., 2024 arXiv:2408.06292), The AI Scientist-v2 eliminates the reliance on human-authored code templates, generalizes effectively across diverse machine learning domains, and leverages a novel progressive agentic tree-search methodology managed by a dedicated experiment manager agent. Additionally, we enhance the AI reviewer component by integrating a Vision-Language Model (VLM) feedback loop for iterative refinement of content and aesthetics of the figures. We evaluated The AI Scientist-v2 by submitting three fully autonomous manuscripts to a peer-reviewed ICLR workshop. Notably, one manuscript achieved high enough scores to exceed the average human acceptance threshold, marking the first instance of a fully AI-generated paper successfully navigating a peer review. This accomplishment highlights the growing capability of AI in conducting all aspects of scientific research. We anticipate that further advancements in autonomous scientific discovery technologies will profoundly impact human knowledge generation, enabling unprecedented scalability in research productivity and significantly accelerating scientific breakthroughs, greatly benefiting society at large. We have open-sourced the code at https://github.com/SakanaAI/AI-Scientist-v2 to foster the future development of this transformative technology. We also discuss the role of AI in science, including AI safety.