Aïra: Rethinking AI Research Assistants for Interdisciplinary Science
For interdisciplinary research teams, this work proposes a new design paradigm for AI assistants, but it is early-stage with no empirical validation.
The paper argues that AI research assistants should be redesigned for interdisciplinary teams, not just individual productivity, and introduces aïra, a system that identifies disciplinary perspectives, translates terminology, and synthesizes collaborative opportunities. No concrete performance numbers are provided.
Scientific discovery increasingly depends on interdisciplinary teams whose members contribute distinct expertise, conceptual frameworks, vocabularies, assumptions, and standards of evidence. Today's AI research assistants are largely designed to support individual researchers through literature review, writing assistance, coding, and data analysis. While these capabilities improve personal productivity, they provide little support for the collaborative reasoning required to integrate knowledge across disciplines. We argue that AI research assistants should evolve from tools that optimize individual workflows to systems designed for interdisciplinary teams. We introduce aïra, an AI research assistant built around this idea. Rather than focusing solely on summarization or question answering, aïra identifies disciplinary perspectives, translates terminology, highlights assumptions, and synthesizes collaborative research opportunities. We describe the design principles underlying aïra, present its system architecture, illustrate its outputs through interdisciplinary research meetings, and outline future research directions for AI systems that support collaborative scholarship.