aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists
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
2025-08-22
Summary
This paper introduces aiXiv, a new platform designed to handle the growing amount of research being created by artificial intelligence. It's a place where both humans and AI can submit, review, and improve scientific work, aiming to speed up the process of scientific discovery.
What's the problem?
Large language models are now capable of doing things like writing research proposals and papers, but the traditional ways we share scientific findings – journals and conferences – aren't really set up to handle this. Human-based peer review is slow and doesn't scale well, and existing online archives like arXiv don't have strong checks to ensure quality. This means a lot of potentially valuable AI-generated research isn't getting out there and used to build on.
What's the solution?
The researchers created aiXiv, which uses a system where both AI and human scientists can work together. AI agents can review proposals and papers, suggest improvements, and even rewrite sections. Humans can do the same, and the platform is designed to easily connect these different 'scientists' through special interfaces. They tested aiXiv and found that it really does improve the quality of AI-generated research through this iterative review process.
Why it matters?
This work is important because it addresses a key bottleneck in the age of AI-driven research. By creating a dedicated platform for AI-generated content, aiXiv could significantly accelerate the pace of scientific progress and make it easier to share and build upon discoveries made by AI, ultimately leading to faster innovation.
Abstract
Recent advances in large language models (LLMs) have enabled AI agents to autonomously generate scientific proposals, conduct experiments, author papers, and perform peer reviews. Yet this flood of AI-generated research content collides with a fragmented and largely closed publication ecosystem. Traditional journals and conferences rely on human peer review, making them difficult to scale and often reluctant to accept AI-generated research content; existing preprint servers (e.g. arXiv) lack rigorous quality-control mechanisms. Consequently, a significant amount of high-quality AI-generated research lacks appropriate venues for dissemination, hindering its potential to advance scientific progress. To address these challenges, we introduce aiXiv, a next-generation open-access platform for human and AI scientists. Its multi-agent architecture allows research proposals and papers to be submitted, reviewed, and iteratively refined by both human and AI scientists. It also provides API and MCP interfaces that enable seamless integration of heterogeneous human and AI scientists, creating a scalable and extensible ecosystem for autonomous scientific discovery. Through extensive experiments, we demonstrate that aiXiv is a reliable and robust platform that significantly enhances the quality of AI-generated research proposals and papers after iterative revising and reviewing on aiXiv. Our work lays the groundwork for a next-generation open-access ecosystem for AI scientists, accelerating the publication and dissemination of high-quality AI-generated research content. Code is available at https://github.com/aixiv-org. Website is available at https://forms.gle/DxQgCtXFsJ4paMtn8.