從AI科學到能動科學：自主科學發現綜述

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

人工智慧（AI）正在重塑科學發現的進程，從專業的計算工具演變為自主的研究夥伴。我們將「代理科學」（Agentic Science）定位為更廣泛的「AI for Science」範式中的一個關鍵階段，在此階段中，AI系統從部分協助進展到完整的科學代理能力。得益於大型語言模型（LLMs）、多模態系統以及整合研究平台的推動，代理型AI展現出在假設生成、實驗設計、執行、分析以及迭代優化等方面的能力——這些行為曾被視為人類獨有的特質。本調查提供了跨生命科學、化學、材料科學和物理學領域的自主科學發現的領域導向回顧。我們通過一個綜合框架，將先前分散的三種視角——過程導向、自主性導向和機制導向——統一起來，該框架連接了基礎能力、核心過程以及領域特定的實現。基於此框架，我們（i）追溯了「AI for Science」的演進歷程，（ii）識別了支撐科學代理能力的五項核心能力，（iii）將發現過程建模為一個動態的四階段工作流程，（iv）回顧了上述領域中的應用案例，以及（v）綜合了關鍵挑戰與未來機遇。這項工作建立了自主科學發現的領域導向綜合，並將「代理科學」定位為推動AI驅動研究的結構化範式。

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.