Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

AiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

Created by
  • Haebom

Author

Pengsong Zhang, Xiang Hu, Guowei Huang, Yang Qi, Heng Zhang, Xiuxu Li, Jiaxing Song, Jiabin Luo, Yijiang Li, Shuo Yin, Chengxiao Dai, Eric Hanchen Jiang, Xiaoyan Zhou, Zhenfei Yin, Boqin Yuan, Jing Dong, Guinan Su, Guanren Qiao, Haiming Tang, Anghong Du, Lili Pan, Zhenzhong Lan, Xinyu Liu

Outline

This paper addresses the challenge that while advances in large-scale language models (LLMs) have enabled AI to autonomously write scientific proposals, conduct experiments, author papers, and conduct peer reviews, existing publishing systems struggle to accommodate this AI-generated research. Existing journals and conferences rely on human peer review, which lack scalability and tend to be reluctant to accept AI-generated research, and existing preprint servers lack rigorous quality control mechanisms. To address these challenges, this paper proposes aiXiv, a next-generation open access platform for both human and AI scientists. aiXiv utilizes a multi-agent architecture to enable the submission, review, and iterative revision of research proposals and papers by both human and AI scientists. It provides APIs and MCP interfaces to facilitate seamless integration between heterogeneous human and AI scientists. Experiments demonstrate that aiXiv is a reliable and robust platform that significantly improves the quality of AI-generated research proposals and papers.

Takeaways, Limitations

•
Takeaways:
◦
Introducing aiXiv, a new open access platform for efficient presentation and distribution of AI-generated research.
◦
Building an effective system for collaboration between human and AI scientists.
◦
Presenting the potential to improve the quality of AI-generated research and accelerate scientific progress.
◦
Presenting the possibility of building a scalable and flexible scientific research ecosystem.
•
Limitations:
◦
The need for verification of the long-term sustainability and maintenance of the aiXiv platform.
◦
Further research is needed to determine the applicability and generalizability of AI-generated research findings across various fields.
◦
There is a need to provide clear solutions to the platform's security and copyright issues.
◦
Consideration needs to be given to issues of bias and fairness in AI review systems.
👍
Made with Slashpage