Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Lianhao, Ling, Hongyi, Fu, Cong, Huang, Yepeng, Sun, Michael, Yu, Wendi, Wang, Xiaoxuan, Li, Xiner, Su, Xingyu, Zhang, Junkai, Chen, Xiusi, Liang, Chenxing, Qian, Xiaofeng, Ji, Heng, Wang, Wei, Zitnik, Marinka, Ji, Shuiwang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908938062004224
author Zhou, Lianhao
Ling, Hongyi
Fu, Cong
Huang, Yepeng
Sun, Michael
Yu, Wendi
Wang, Xiaoxuan
Li, Xiner
Su, Xingyu
Zhang, Junkai
Chen, Xiusi
Liang, Chenxing
Qian, Xiaofeng
Ji, Heng
Wang, Wei
Zitnik, Marinka
Ji, Shuiwang
author_facet Zhou, Lianhao
Ling, Hongyi
Fu, Cong
Huang, Yepeng
Sun, Michael
Yu, Wendi
Wang, Xiaoxuan
Li, Xiner
Su, Xingyu
Zhang, Junkai
Chen, Xiusi
Liang, Chenxing
Qian, Xiaofeng
Ji, Heng
Wang, Wei
Zitnik, Marinka
Ji, Shuiwang
contents Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accelerate discovery across varying levels of autonomy. These language agents provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics. This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle, from hypothesis discovery, experimental design and execution, to result analysis and refinement. We critically examine current methodologies, emphasizing key innovations, practical achievements, and outstanding limitations. Additionally, we identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents. Our analysis highlights the transformative potential of autonomous agents to accelerate scientific discovery across diverse domains.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09901
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
Zhou, Lianhao
Ling, Hongyi
Fu, Cong
Huang, Yepeng
Sun, Michael
Yu, Wendi
Wang, Xiaoxuan
Li, Xiner
Su, Xingyu
Zhang, Junkai
Chen, Xiusi
Liang, Chenxing
Qian, Xiaofeng
Ji, Heng
Wang, Wei
Zitnik, Marinka
Ji, Shuiwang
Artificial Intelligence
Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accelerate discovery across varying levels of autonomy. These language agents provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics. This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle, from hypothesis discovery, experimental design and execution, to result analysis and refinement. We critically examine current methodologies, emphasizing key innovations, practical achievements, and outstanding limitations. Additionally, we identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents. Our analysis highlights the transformative potential of autonomous agents to accelerate scientific discovery across diverse domains.
title Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
topic Artificial Intelligence
url https://arxiv.org/abs/2510.09901