Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.14111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909855791448064 |
|---|---|
| author | Wei, Jiaqi Yang, Yuejin Zhang, Xiang Chen, Yuhan Zhuang, Xiang Gao, Zhangyang Zhou, Dongzhan Wang, Guangshuai Gao, Zhiqiang Cao, Juntai Qiu, Zijie Hu, Ming Ma, Chenglong Tang, Shixiang He, Junjun Song, Chunfeng He, Xuming Zhang, Qiang You, Chenyu Zheng, Shuangjia Ding, Ning Ouyang, Wanli Dong, Nanqing Cheng, Yu Sun, Siqi Bai, Lei Zhou, Bowen |
| author_facet | Wei, Jiaqi Yang, Yuejin Zhang, Xiang Chen, Yuhan Zhuang, Xiang Gao, Zhangyang Zhou, Dongzhan Wang, Guangshuai Gao, Zhiqiang Cao, Juntai Qiu, Zijie Hu, Ming Ma, Chenglong Tang, Shixiang He, Junjun Song, Chunfeng He, Xuming Zhang, Qiang You, Chenyu Zheng, Shuangjia Ding, Ning Ouyang, Wanli Dong, Nanqing Cheng, Yu Sun, Siqi Bai, Lei Zhou, Bowen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery Wei, Jiaqi Yang, Yuejin Zhang, Xiang Chen, Yuhan Zhuang, Xiang Gao, Zhangyang Zhou, Dongzhan Wang, Guangshuai Gao, Zhiqiang Cao, Juntai Qiu, Zijie Hu, Ming Ma, Chenglong Tang, Shixiang He, Junjun Song, Chunfeng He, Xuming Zhang, Qiang You, Chenyu Zheng, Shuangjia Ding, Ning Ouyang, Wanli Dong, Nanqing Cheng, Yu Sun, Siqi Bai, Lei Zhou, Bowen Machine Learning 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. |
| title | From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.14111 |