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

arXiv 2025 52.4 method

TLDR

aiXiv is an open-access platform with multi-agent architecture for submitting, reviewing, and iteratively refining AI-generated research proposals and papers.

Reasoning

The paper addresses a timely problem of disseminating AI-generated research and proposes a concrete platform with multi-agent review. Strengths include a clear motivation and experimental evidence of quality improvement. Weaknesses are the lack of detailed experimental methodology and potential biases in AI self-review.

Read-first score

Read-first score 52.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 61.

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Topical relevance 42%

50.8

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=experiment

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 62.

Keyword Scores

AI scientist

automated scientific discovery

AI for scientific research

scientific discovery agent

automated research

research automation

paper writing agent

autonomous research agent

automated experimentation

literature review agent

survey generation

experiment design agent

Deep Analysis

Innovations

Multi-agent architecture enabling submission, review, and iterative refinement of research by both human and AI scientists
API and MCP interfaces for seamless integration of heterogeneous human and AI scientists into a scalable ecosystem
Next-generation open-access platform specifically designed to host and improve AI-generated scientific content

Methodology

The authors built aiXiv, a platform with a multi-agent architecture that allows research proposals and papers to be submitted, reviewed, and iteratively refined by human and AI agents. They conducted extensive experiments to evaluate the platform's reliability and its effect on the quality of AI-generated research after iterative revising and reviewing.

Key Results

aiXiv significantly enhances the quality of AI-generated research proposals and papers through its iterative review and revision process, demonstrating reliability and robustness as a publication platform.

Resources

Paper