The Design Space of Recent AI-assisted Research Tools for Ideation, Sensemaking, and Scientific Creativity

2025-02-22

AI Summary

This study addresses the risk that AI-assisted research tools may exacerbate automation bias and undermine critical thinking. We systematically analyze 11 representative HCI tools (5 traditional AI, 6 generative AI) published between 2021–2023, focusing on creative ideation, meaning-making, and scientific creativity support. Through a literature review of HCI research and functional reverse engineering—grounded in cognitive science—we construct a design space model encompassing LLMs, retrieval-augmented generation, and knowledge graphs. We propose, for the first time, four cognition-centered design principles: user agency, support for divergent-convergent thinking, adaptive flexibility, and transparency with accuracy—shifting AI’s role from workflow mimicry to human-AI co-creation. The resulting transferable design recommendations provide empirically grounded guidance for developing next-generation AI research tools that mitigate cognitive risks and enhance scientific creativity. (149 words)

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Generative AI (GenAI) tools are radically expanding the scope and capability of automation in knowledge work such as academic research. AI-assisted research tools show promise for augmenting human cognition and streamlining research processes, but could potentially increase automation bias and stifle critical thinking. We surveyed the past three years of publications from leading HCI venues. We closely examined 11 AI-assisted research tools, five employing traditional AI approaches and six integrating GenAI, to explore how these systems envision novel capabilities and design spaces. We consolidate four design recommendations that inform cognitive engagement when working with an AI research tool: Providing user agency and control; enabling divergent and convergent thinking; supporting adaptability and flexibility; and ensuring transparency and accuracy. We discuss how these ideas mark a shift in AI-assisted research tools from mimicking a researcher's established workflows to generative co-creation with the researcher and the opportunities this shift affords the research community.

Problem

• AI-assisted research tools design
• Cognitive engagement in AI tools
• Generative co-creation in research

Innovation

• Generative AI tools
• Cognitive engagement design
• Generative co-creation shift