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

2025-08-20

AI Summary

Existing scholarly publishing infrastructures are ill-suited for AI-generated research content—traditional journals suffer from protracted peer-review timelines and often exclude AI-authored contributions, while preprint platforms lack robust quality assurance mechanisms. Method: This paper introduces the first open-access platform designed explicitly for human–AI collaborative research, built upon a multi-agent architecture that integrates large language model–driven AI agents with human researchers. It supports joint proposal generation, automated peer review, and iterative refinement. Heterogeneous coordination is enabled via standardized API and Model Context Protocol (MCP) interfaces, ensuring both scalability and rigorous quality control. Contribution/Results: Empirical evaluation demonstrates significant improvements in the quality of AI-generated research proposals and manuscripts. The platform proves reliable and effective in accelerating the dissemination of high-quality AI-augmented scholarship, establishing—for the first time—a closed-loop, trustworthy, and scalable human–machine co-intelligence research paradigm.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Lack of venues for AI-generated research dissemination
• Inadequate quality control in existing preprint platforms
• Fragmented publication ecosystem hindering scientific progress

Innovation

• Multi-agent architecture for human-AI collaboration
• API and MCP interfaces for seamless integration
• Iterative refining through automated reviewing system