{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/3e82f301-2023-4c1a-9ab0-b4ca864f538e","identifier":"3e82f301-2023-4c1a-9ab0-b4ca864f538e","url":"https://forgecascade.org/public/capsules/3e82f301-2023-4c1a-9ab0-b4ca864f538e","name":"AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists","text":"# AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists\n\n**Authors:** Junshu Pan, Panzhong Lu, Yixuan Weng, Qiyao Sun, Fang Guo\n**arXiv:** https://arxiv.org/abs/2605.21481v1\n**Published:** 2026-05-20T17:59:03Z\n\n## Abstract\nRecent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs, placing increasing strain on traditional academic publishing systems and challenging the scalability of conference- and journal-centered paradigms amid rising submission volumes, reviewer workload, and venue size. To address these challenges, we explore an AI-era publishing paradigm in which both human and AI scientists participate as authors and readers, and papers evolve through continuous, feedback-driven iteration. We propose AiraXiv, an AI-driven open-access platform built on open preprints, AI-augmented analysis and review, and reader feedback. AiraXiv supports human scientists through an interactive UI and AI scientists through Model Context Protocol (MCP)-based interactions. We validate AiraXiv through real-world deployments, including serving as the submission platform for ICAIS 2025, demonstrating its potential as a fast, inclusive, and scalable research infrastructure for the AI era. AiraXiv is publicly available at https://airaxiv.com.","keywords":["cs.AI","cs.CL","cs.LG"],"about":[{"@type":"Thing","name":"autoinducer AI-2 transmembrane transport"},{"@type":"Thing","name":"type 2 metabotropic glutamate receptor binding"},{"@type":"Thing","name":"Defective SLC24A4 causes hypomineralized amelogenesis imperfecta (AI)"},{"@type":"Thing","name":"Decreased circulating apolipoprotein AI concentration"},{"@type":"Thing","name":"Donut"},{"@type":"Thing","name":"Rising Sun"},{"@type":"Thing","name":"Arp"},{"@type":"Thing","name":"Artificial Intelligence"},{"@type":"Thing","name":"Cloud Service Hijacking"},{"@type":"Thing","name":"Additional Cloud Credentials"},{"@type":"Thing","name":"Malteiro"},{"@type":"Thing","name":"Kimsuky"}],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-21T06:00:06.253000Z","dateModified":"2026-05-21T06:00:06.253000Z","isBasedOn":"https://arxiv.org/abs/2605.21481v1","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":65},{"@type":"PropertyValue","name":"verification_status","value":"source_linked"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"}]}