From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery

TL;DR

The rapid evolution of LLMs is driving a shift toward autonomous roles in scientific discovery. The paper introduces a three-level autonomy taxonomy (Tool, Analyst, Scientist) and maps LLM activities to the six stages of the scientific method, surveying a broad set of tools, benchmarks, and architectures. It identifies core contributions in structuring the autonomy landscape, assessing current capabilities, and outlining pivotal challenges—robotic automation, continuous self-improvement, transparency, and governance—for responsible advancement. The framework provides a foundation for designing, evaluating, and governing AI-driven scientific workflows at scale.

Abstract

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.

Figures (2)

• Figure 1: Stages of the scientific method with corresponding LLM applications and research topics.
• Figure 2: Taxonomy of research works in LLM-based scientific discovery with detailed categorization.