From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
It provides a conceptual framework for researchers and practitioners to understand and guide the role of LLMs in science, though it is incremental as a survey.
This survey introduces a three-level taxonomy (Tool, Analyst, Scientist) to describe the increasing autonomy of Large Language Models (LLMs) in scientific discovery, charting their evolution from automation tools to autonomous agents and outlining future challenges like robotic automation and ethical governance.
Large Language Models (LLMs) are catalyzing a paradigm shift in scientific discovery, evolving from task-specific automation tools into increasingly autonomous agents and fundamentally redefining research processes and human-AI collaboration. This survey systematically charts this burgeoning field, placing a central focus on the changing roles and escalating capabilities of LLMs in science. Through the lens of the scientific method, we introduce a foundational three-level taxonomy-Tool, Analyst, and Scientist-to delineate their escalating autonomy and evolving responsibilities within the research lifecycle. We further identify pivotal challenges and future research trajectories such as robotic automation, self-improvement, and ethical governance. Overall, this survey provides a conceptual architecture and strategic foresight to navigate and shape the future of AI-driven scientific discovery, fostering both rapid innovation and responsible advancement. Github Repository: https://github.com/HKUST-KnowComp/Awesome-LLM-Scientific-Discovery.