Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
This addresses inefficiencies in AI for Science by introducing a scalable automation framework for researchers, though it is conceptual and incremental in proposing a classification system.
The paper proposes Agent4S, a framework using LLM-driven agents to automate entire scientific research workflows, aiming to transform it into a new paradigm for enhanced efficiency and discovery.
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.