从AI赋能科学到自主科学：关于自动化科学发现的综述

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

August 18, 2025

作者: Jiaqi Wei, Yuejin Yang, Xiang Zhang, Yuhan Chen, Xiang Zhuang, Zhangyang Gao, Dongzhan Zhou, Guangshuai Wang, Zhiqiang Gao, Juntai Cao, Zijie Qiu, Xuming He, Qiang Zhang, Chenyu You, Shuangjia Zheng, Ning Ding, Wanli Ouyang, Nanqing Dong, Yu Cheng, Siqi Sun, Lei Bai, Bowen Zhou

cs.AI

摘要

人工智能（AI）正在重塑科学发现，从专业化的计算工具演变为自主的研究伙伴。我们将“代理科学”定位为更广泛的“AI for Science”范式中的一个关键阶段，在此阶段，AI系统从部分辅助迈向全面的科学代理能力。借助大型语言模型（LLMs）、多模态系统及集成研究平台，代理型AI展现出在假设生成、实验设计、执行、分析及迭代优化等方面的能力——这些曾被视为人类独有的行为。本综述以领域为导向，回顾了生命科学、化学、材料科学及物理学中的自主科学发现。我们通过一个综合框架，将先前分散的三种视角——过程导向、自主导向及机制导向——统一起来，该框架连接了基础能力、核心过程及领域特定的实现。基于此框架，我们（i）追溯了“AI for Science”的演进历程，（ii）识别了支撑科学代理能力的五大核心能力，（iii）将发现过程建模为一个动态的四阶段工作流，（iv）评述了上述领域中的应用实例，以及（v）综合了关键挑战与未来机遇。本研究确立了自主科学发现的领域导向综合，并将“代理科学”定位为推进AI驱动研究的一个结构化范式。

English

Artificial intelligence (AI) is reshaping scientific discovery, evolving from specialized computational tools into autonomous research partners. We position Agentic Science as a pivotal stage within the broader AI for Science paradigm, where AI systems progress from partial assistance to full scientific agency. Enabled by large language models (LLMs), multimodal systems, and integrated research platforms, agentic AI shows capabilities in hypothesis generation, experimental design, execution, analysis, and iterative refinement -- behaviors once regarded as uniquely human. This survey provides a domain-oriented review of autonomous scientific discovery across life sciences, chemistry, materials science, and physics. We unify three previously fragmented perspectives -- process-oriented, autonomy-oriented, and mechanism-oriented -- through a comprehensive framework that connects foundational capabilities, core processes, and domain-specific realizations. Building on this framework, we (i) trace the evolution of AI for Science, (ii) identify five core capabilities underpinning scientific agency, (iii) model discovery as a dynamic four-stage workflow, (iv) review applications across the above domains, and (v) synthesize key challenges and future opportunities. This work establishes a domain-oriented synthesis of autonomous scientific discovery and positions Agentic Science as a structured paradigm for advancing AI-driven research.