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

arXiv: https://arxiv.org/abs/2502.16291 · HTML: https://mlsanity.com/paper/2502.16291/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Builds on (most cited first, 5 of 5)

- [Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy](https://mlsanity.com/paper/2002.04087/) (2020)
- [IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback](https://mlsanity.com/paper/2410.04025/) (2024)
- [CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent](https://mlsanity.com/paper/2310.06155/) (2023)
- [PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers](https://mlsanity.com/paper/2403.02939/) (2024)
- [Scholastic: Graphical Human-Al Collaboration for Inductive and Interpretive Text Analysis](https://mlsanity.com/paper/2208.06133/) (2022)

## Built on by (most cited first, 3 of 3)

- [ScholarMate: A Mixed-Initiative Tool for Qualitative Knowledge Work and Information Sensemaking](https://mlsanity.com/paper/2504.14406/) (2025)
- [TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models](https://mlsanity.com/paper/2507.18945/) (2025)
- [Learning Individual Scientific Taste with Privileged Hindsight Distillation](https://mlsanity.com/paper/2610.19719/) (2026)

## Abstract (arXiv)

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.