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

2025-05-19

AI Summary

This paper addresses the paradigm shift arising from large language models (LLMs) evolving from research aids to autonomous scientific agents. Method: Through a systematic literature review and interdisciplinary analysis—integrating philosophy of science, human-AI collaboration theory, and AI governance—we propose the first three-tiered autonomy framework for LLMs in scientific discovery (Tool → Analyst → Scientist), rigorously delineating capability boundaries and evolutionary trajectories across the full scientific workflow: hypothesis generation, experimental design, and self-reflection. We anchor our conceptual architecture and technical roadmap in scientific methodology. Contribution/Results: The work delivers the field’s first comprehensive survey, establishes foundational theoretical grounding for autonomous scientific agents, and releases Awesome-LLM-Scientific-Discovery—an open-source knowledge repository supporting both theoretical advancement and practical development.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• LLMs' evolving roles in scientific discovery
• Autonomy levels of LLMs in research
• Challenges in AI-driven scientific innovation

Innovation

• LLMs evolve from tools to autonomous science agents
• Three-level taxonomy: Tool, Analyst, Scientist autonomy
• Focus on robotic automation, self-improvement, ethics