InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| 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 |