OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911318063185920 |
|---|---|
| author | Shao, Chenyang Huang, Dehao Li, Yu Zhao, Keyu Lin, Weiquan Zhang, Yining Zeng, Qingbin Chen, Zhiyu Li, Tianxing Huang, Yifei Wu, Taozhong Liu, Xinyang Zhao, Ruotong Zhao, Mengsheng Li, Jiaoyang Zhang, Xuhua Wang, Yue Zhen, Yuanyi Xu, Fengli Li, Yong Liu, Tie-Yan |
| author_facet | Shao, Chenyang Huang, Dehao Li, Yu Zhao, Keyu Lin, Weiquan Zhang, Yining Zeng, Qingbin Chen, Zhiyu Li, Tianxing Huang, Yifei Wu, Taozhong Liu, Xinyang Zhao, Ruotong Zhao, Mengsheng Li, Jiaoyang Zhang, Xuhua Wang, Yue Zhen, Yuanyi Xu, Fengli Li, Yong Liu, Tie-Yan |
| contents | With the rapid development of Large Language Models (LLMs), AI agents have demonstrated increasing proficiency in scientific tasks, ranging from hypothesis generation and experimental design to manuscript writing. Such agent systems are commonly referred to as "AI Scientists." However, existing AI Scientists predominantly formulate scientific discovery as a standalone search or optimization problem, overlooking the fact that scientific research is inherently a social and collaborative endeavor. Real-world science relies on a complex scientific infrastructure composed of collaborative mechanisms, contribution attribution, peer review, and structured scientific knowledge networks. Due to the lack of modeling for these critical dimensions, current systems struggle to establish a genuine research ecosystem or interact deeply with the human scientific community. To bridge this gap, we introduce OmniScientist, a framework that explicitly encodes the underlying mechanisms of human research into the AI scientific workflow. OmniScientist not only achieves end-to-end automation across data foundation, literature review, research ideation, experiment automation, scientific writing, and peer review, but also provides comprehensive infrastructural support by simulating the human scientific system, comprising: (1) a structured knowledge system built upon citation networks and conceptual correlations; (2) a collaborative research protocol (OSP), which enables seamless multi-agent collaboration and human researcher participation; and (3) an open evaluation platform (ScienceArena) based on blind pairwise user voting and Elo rankings. This infrastructure empowers agents to not only comprehend and leverage human knowledge systems but also to collaborate and co-evolve, fostering a sustainable and scalable innovation ecosystem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16931 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists Shao, Chenyang Huang, Dehao Li, Yu Zhao, Keyu Lin, Weiquan Zhang, Yining Zeng, Qingbin Chen, Zhiyu Li, Tianxing Huang, Yifei Wu, Taozhong Liu, Xinyang Zhao, Ruotong Zhao, Mengsheng Li, Jiaoyang Zhang, Xuhua Wang, Yue Zhen, Yuanyi Xu, Fengli Li, Yong Liu, Tie-Yan Computers and Society Computational Engineering, Finance, and Science Computation and Language With the rapid development of Large Language Models (LLMs), AI agents have demonstrated increasing proficiency in scientific tasks, ranging from hypothesis generation and experimental design to manuscript writing. Such agent systems are commonly referred to as "AI Scientists." However, existing AI Scientists predominantly formulate scientific discovery as a standalone search or optimization problem, overlooking the fact that scientific research is inherently a social and collaborative endeavor. Real-world science relies on a complex scientific infrastructure composed of collaborative mechanisms, contribution attribution, peer review, and structured scientific knowledge networks. Due to the lack of modeling for these critical dimensions, current systems struggle to establish a genuine research ecosystem or interact deeply with the human scientific community. To bridge this gap, we introduce OmniScientist, a framework that explicitly encodes the underlying mechanisms of human research into the AI scientific workflow. OmniScientist not only achieves end-to-end automation across data foundation, literature review, research ideation, experiment automation, scientific writing, and peer review, but also provides comprehensive infrastructural support by simulating the human scientific system, comprising: (1) a structured knowledge system built upon citation networks and conceptual correlations; (2) a collaborative research protocol (OSP), which enables seamless multi-agent collaboration and human researcher participation; and (3) an open evaluation platform (ScienceArena) based on blind pairwise user voting and Elo rankings. This infrastructure empowers agents to not only comprehend and leverage human knowledge systems but also to collaborate and co-evolve, fostering a sustainable and scalable innovation ecosystem. |
| title | OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists |
| topic | Computers and Society Computational Engineering, Finance, and Science Computation and Language |
| url | https://arxiv.org/abs/2511.16931 |