A Self-Evolving AI Agent System for Climate Science
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908623853060096 |
|---|---|
| author | Guo, Zijie Wang, Jiong Ling, Fenghua Wei, Wangxu Yue, Xiaoyu Jiang, Zhe Xu, Wanghan Luo, Jing-Jia Cheng, Lijing Ham, Yoo-Geun Song, Fengfei Gentine, Pierre Yamagata, Toshio Fei, Ben Zhang, Wenlong Gu, Xinyu Li, Chao Wang, Yaqiang Chen, Tao Ouyang, Wanli Zhou, Bowen Bai, Lei |
| author_facet | Guo, Zijie Wang, Jiong Ling, Fenghua Wei, Wangxu Yue, Xiaoyu Jiang, Zhe Xu, Wanghan Luo, Jing-Jia Cheng, Lijing Ham, Yoo-Geun Song, Fengfei Gentine, Pierre Yamagata, Toshio Fei, Ben Zhang, Wenlong Gu, Xinyu Li, Chao Wang, Yaqiang Chen, Tao Ouyang, Wanli Zhou, Bowen Bai, Lei |
| contents | Scientific progress in Earth science depends on integrating data across the planet's interconnected spheres. However, the accelerating volume and fragmentation of multi-sphere knowledge and data have surpassed human analytical capacity. This creates a major bottleneck for discovery, especially in climate science. To address this challenge, we introduce EarthLink, the first self-evolving AI agent system designed as an interactive "copilot" for Earth scientists. Through natural language interaction, EarthLink automates the entire research workflow by integrating planning, code execution, data analysis, and physical reasoning into a unified process that directly addresses this limitation. Beyond efficiency, it exhibits human-like cross-disciplinary analytical ability and achieves proficiency comparable to a junior researcher in expert evaluations on core large-scale climate tasks, including model-observation comparison and climate change understanding. When tasked with an open scientific problem, specifically the discovery of precursors of the Atlantic Niño, EarthLink autonomously developed a research strategy, identified sources of predictability, verified its hypotheses with available data, and proposed a physically consistent mechanism. These emerging capabilities enable a new human-AI research paradigm. Scientists can focus on value and result judgments, while AI systems handle complex data analysis and knowledge integration. This accelerates the pace and breadth of discovery in Earth sciences. The system is accessible at our website https://earthlink.intern-ai.org.cn. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Self-Evolving AI Agent System for Climate Science Guo, Zijie Wang, Jiong Ling, Fenghua Wei, Wangxu Yue, Xiaoyu Jiang, Zhe Xu, Wanghan Luo, Jing-Jia Cheng, Lijing Ham, Yoo-Geun Song, Fengfei Gentine, Pierre Yamagata, Toshio Fei, Ben Zhang, Wenlong Gu, Xinyu Li, Chao Wang, Yaqiang Chen, Tao Ouyang, Wanli Zhou, Bowen Bai, Lei Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Scientific progress in Earth science depends on integrating data across the planet's interconnected spheres. However, the accelerating volume and fragmentation of multi-sphere knowledge and data have surpassed human analytical capacity. This creates a major bottleneck for discovery, especially in climate science. To address this challenge, we introduce EarthLink, the first self-evolving AI agent system designed as an interactive "copilot" for Earth scientists. Through natural language interaction, EarthLink automates the entire research workflow by integrating planning, code execution, data analysis, and physical reasoning into a unified process that directly addresses this limitation. Beyond efficiency, it exhibits human-like cross-disciplinary analytical ability and achieves proficiency comparable to a junior researcher in expert evaluations on core large-scale climate tasks, including model-observation comparison and climate change understanding. When tasked with an open scientific problem, specifically the discovery of precursors of the Atlantic Niño, EarthLink autonomously developed a research strategy, identified sources of predictability, verified its hypotheses with available data, and proposed a physically consistent mechanism. These emerging capabilities enable a new human-AI research paradigm. Scientists can focus on value and result judgments, while AI systems handle complex data analysis and knowledge integration. This accelerates the pace and breadth of discovery in Earth sciences. The system is accessible at our website https://earthlink.intern-ai.org.cn. |
| title | A Self-Evolving AI Agent System for Climate Science |
| topic | Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2507.17311 |