A Survey of AI Scientists
Guiyao Tie, Pan Zhou, Lichao Sun

TL;DR
This survey reviews the evolution of AI systems acting as autonomous scientists, introducing a six-stage framework to understand their development, challenges, and future directions in transforming scientific discovery.
Contribution
It presents a unified six-stage methodological framework for autonomous scientific systems and synthesizes recent advancements from foundational modules to scalable, collaborative AI scientists.
Findings
Field evolved from foundational modules to integrated systems
Current frontier focuses on scalability, impact, and human-AI collaboration
Identifies challenges in robustness and governance
Abstract
Artificial intelligence is undergoing a profound transition from a computational instrument to an autonomous originator of scientific knowledge. This emerging paradigm, the AI scientist, is architected to emulate the complete scientific workflow-from initial hypothesis generation to the final synthesis of publishable findings-thereby promising to fundamentally reshape the pace and scale of discovery. However, the rapid and unstructured proliferation of these systems has created a fragmented research landscape, obscuring overarching methodological principles and developmental trends. This survey provides a systematic and comprehensive synthesis of this domain by introducing a unified, six-stage methodological framework that deconstructs the end-to-end scientific process into: Literature Review, Idea Generation, Experimental Preparation, Experimental Execution, Scientific Writing, and…
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
TopicsArtificial Intelligence in Healthcare and Education · Scientific Computing and Data Management · Ethics and Social Impacts of AI
