InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: InternAgent Team, Zhang, Bo, Feng, Shiyang, Yan, Xiangchao, Yuan, Jiakang, Ma, Runmin, Hu, Yusong, Yu, Zhiyin, He, Xiaohan, Huang, Songtao, Hou, Shaowei, Nie, Zheng, Wang, Zhilong, Liu, Jinyao, Peng, Tianshuo, Ye, Peng, Zhou, Dongzhan, Zhang, Shufei, Wang, Xiaosong, Zhang, Yilan, Li, Meng, Tu, Zhongying, Yue, Xiangyu, Ouyang, Wangli, Zhou, Bowen, Bai, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913953691467776
author InternAgent Team
Zhang, Bo
Feng, Shiyang
Yan, Xiangchao
Yuan, Jiakang
Ma, Runmin
Hu, Yusong
Yu, Zhiyin
He, Xiaohan
Huang, Songtao
Hou, Shaowei
Nie, Zheng
Wang, Zhilong
Liu, Jinyao
Peng, Tianshuo
Ye, Peng
Zhou, Dongzhan
Zhang, Shufei
Wang, Xiaosong
Zhang, Yilan
Li, Meng
Tu, Zhongying
Yue, Xiangyu
Ouyang, Wangli
Zhou, Bowen
Bai, Lei
author_facet InternAgent Team
Zhang, Bo
Feng, Shiyang
Yan, Xiangchao
Yuan, Jiakang
Ma, Runmin
Hu, Yusong
Yu, Zhiyin
He, Xiaohan
Huang, Songtao
Hou, Shaowei
Nie, Zheng
Wang, Zhilong
Liu, Jinyao
Peng, Tianshuo
Ye, Peng
Zhou, Dongzhan
Zhang, Shufei
Wang, Xiaosong
Zhang, Yilan
Li, Meng
Tu, Zhongying
Yue, Xiangyu
Ouyang, Wangli
Zhou, Bowen
Bai, Lei
contents Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce InternAgent, a unified closed-loop multi-agent framework to conduct Autonomous Scientific Research (ASR) across various scientific research fields, enabling researchers to tackle complicated problems in these fields with unprecedented speed and precision. InternAgent highlights three key advantages: 1) Scalability: InternAgent has demonstrated its versatility across 12 scientific research tasks, capable of generating innovative ideas to enhance the performance of baseline code. 2) Interactivity: InternAgent provides an interface for human expert feedback and multi-agent interaction in automated end-to-end processes, allowing for the seamless integration of domain expert knowledge. 3) Efficiency: InternAgent has achieved promising performance gains in several scientific fields with significantly less time cost compared to human efforts. For instance, in reaction yield prediction, it increased from 27.6% to 35.4% in just 12 hours; in enhancer activity prediction, accuracy rose from 0.65 to 0.79 with only 4 hours of processing; and in 2D semantic segmentation, precision advanced from 78.8% to 81.0% in a mere 30 hours.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16938
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
InternAgent Team
Zhang, Bo
Feng, Shiyang
Yan, Xiangchao
Yuan, Jiakang
Ma, Runmin
Hu, Yusong
Yu, Zhiyin
He, Xiaohan
Huang, Songtao
Hou, Shaowei
Nie, Zheng
Wang, Zhilong
Liu, Jinyao
Peng, Tianshuo
Ye, Peng
Zhou, Dongzhan
Zhang, Shufei
Wang, Xiaosong
Zhang, Yilan
Li, Meng
Tu, Zhongying
Yue, Xiangyu
Ouyang, Wangli
Zhou, Bowen
Bai, Lei
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce InternAgent, a unified closed-loop multi-agent framework to conduct Autonomous Scientific Research (ASR) across various scientific research fields, enabling researchers to tackle complicated problems in these fields with unprecedented speed and precision. InternAgent highlights three key advantages: 1) Scalability: InternAgent has demonstrated its versatility across 12 scientific research tasks, capable of generating innovative ideas to enhance the performance of baseline code. 2) Interactivity: InternAgent provides an interface for human expert feedback and multi-agent interaction in automated end-to-end processes, allowing for the seamless integration of domain expert knowledge. 3) Efficiency: InternAgent has achieved promising performance gains in several scientific fields with significantly less time cost compared to human efforts. For instance, in reaction yield prediction, it increased from 27.6% to 35.4% in just 12 hours; in enhancer activity prediction, accuracy rose from 0.65 to 0.79 with only 4 hours of processing; and in 2D semantic segmentation, precision advanced from 78.8% to 81.0% in a mere 30 hours.
title InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.16938