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

TL;DR

Generative AI tools promise to augment research but risk automation bias and diminished critical thinking. The authors survey 13 AI-assisted research tools from CHI venues (2022–2024), categorize them into traditional AI, customized transformers, and open-access LLMs, and extract four design dimensions that shape cognitive engagement. They propose four design recommendations—enhancing user agency and control, supporting distinct divergent/convergent thinking modes, ensuring adaptability, and maintaining accuracy and transparency—and distinguish between workflow-mimicry and generative co-creation. The work provides a design-space map to guide future AI-driven research interfaces, aiming to preserve human interpretation and critical thinking while leveraging GenAI’s creative potential in ideation, sensemaking, and scientific creativity.

Abstract

Generative AI (GenAI) tools are radically expanding the scope and capability of automation in knowledge work such as academic research. While promising for augmenting cognition and streamlining processes, AI-assisted research tools may also increase automation bias and hinder critical thinking. To examine recent developments, we surveyed publications from leading HCI venues over the past three years, closely analyzing thirteen tools to better understand the novel capabilities of these AI-assisted systems and the design spaces they enable: seven employing traditional AI or customized transformer-based approaches, and six integrating open-access large language models (LLMs). Our analysis characterizes the emerging design space, distinguishes between tools focused on workflow mimicry versus generative exploration, and yields four critical design recommendations to guide the development of future systems that foster meaningful cognitive engagement: providing user agency and control, differentiating divergent/convergent thinking support, ensuring adaptability, and prioritizing transparency/accuracy. This work discusses how these insights signal a shift from mere workflow replication towards generative co-creation, presenting new opportunities for the community to craft intuitive, AI-driven research interfaces and interactions.