Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
Boyuan Zheng, Zerui Fang, Zhe Xu, Rui Wang, Yiwen Chen, Cunshi Wang, Mengwei Qu, Lei Lei, Zhen Feng, Yan Liu, Yuyang Li, Mingzhou Tan, Jiaji Wu, Jianwei Shuai, Jia Li, Fangfu Ye

TL;DR
This paper proposes Agent4S, a new paradigm using large language model-driven agents to automate scientific research workflows, aiming to revolutionize scientific discovery as the fifth paradigm.
Contribution
It introduces a five-level classification framework for Agent4S, outlining a progression from basic automation to fully autonomous AI scientists.
Findings
Defines a five-level classification for Agent4S
Outlines a roadmap from simple automation to autonomous AI scientists
Proposes Agent4S as the next scientific paradigm
Abstract
While AI for Science (AI4S) serves as an analytical tool in the current research paradigm, it doesn't solve its core inefficiency. We propose "Agent for Science" (Agent4S)-the use of LLM-driven agents to automate the entire research workflow-as the true Fifth Scientific Paradigm. This paper introduces a five-level classification for Agent4S, outlining a clear roadmap from simple task automation to fully autonomous, collaborative "AI Scientists." This framework defines the next revolutionary step in scientific discovery.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Scientific Computing and Data Management · Machine Learning in Materials Science
