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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Tianshi, Deng, Zheye, Tsang, Hong Ting, Wang, Weiqi, Bai, Jiaxin, Wang, Zihao, Song, Yangqiu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916954072154112
author Zheng, Tianshi
Deng, Zheye
Tsang, Hong Ting
Wang, Weiqi
Bai, Jiaxin
Wang, Zihao
Song, Yangqiu
author_facet Zheng, Tianshi
Deng, Zheye
Tsang, Hong Ting
Wang, Weiqi
Bai, Jiaxin
Wang, Zihao
Song, Yangqiu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13259
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
Zheng, Tianshi
Deng, Zheye
Tsang, Hong Ting
Wang, Weiqi
Bai, Jiaxin
Wang, Zihao
Song, Yangqiu
Computation and Language
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.
title From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
topic Computation and Language
url https://arxiv.org/abs/2505.13259