Problem
Research questions and friction points this paper is trying to address.
scientific data analysis
knowledge integration
complex datasets
domain expertise
AI support
From Overload to Insights: How AI Agents Can Support Scientists in Analyzing Complex Data
🤖 AI Summary
This study addresses the challenges of fragmented domain knowledge and dispersed tool documentation in scientific data analysis at the European XFEL by integrating design science research, user-centered design, and high-performance computing environments. Through a literature review, tool assessment, and user interviews, the authors developed and evaluated two specialized AI agent prototypes—one for knowledge retrieval and the other for source code generation. The work proposes a requirements specification and adaptive, evolvable design principles for AI agents tailored to scientific data analysis, thereby filling a critical gap in maintainable AI support systems for highly specialized research contexts. Empirical evaluation demonstrates that these agents effectively enhance both the efficiency and accuracy of data processing workflows.
📝 Abstract
Scientists at European XFEL conduct experiments that generate very large and complex datasets. The subsequent data analysis is challenging as scientists must combine their domain expertise with facility- and software-specific knowledge scattered across documentation, tools, and support channels. To address this problem, we designed and evaluated an agentic AI system tailored to the scientists' needs and integrated with the high-performance computing environment of European XFEL. Using a design science research approach, we conducted a rapid literature review, a systematic evaluation of 16 AI tools, multiple interviews, a focus group, and a user study with experts at European XFEL to develop and evaluate two prototypes. Our study identifies key knowledge challenges in scientific data analysis, derives requirements for an AI agent that supports knowledge retrieval and source code generation, and proposes design recommendations for a specialized system adaptable to the evolving AI tool landscape. These findings provide guidance for developing maintainable AI support in highly specialized scientific environments.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI agents
scientific data analysis
knowledge retrieval
code generation
design science research
🔎 Similar Papers
fetch failed
