Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models

2025/06/30 by Zheng, Boyuan, Fang, Zerui, Xu, Zhe +13
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2506.23692

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.

Citations

• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
• Scientific discovery in the age of artificial intelligence
• Breaking the Curse of Dimensionality with Convex Neural Networks
• XXI. Experiments to determine the density of the earth

Related

• From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
• Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
• Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
• ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
• From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery