Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
Alex Bäuerle, Adam Connors, Alexander Novikov, Adam Zsolt Wagner, Ngân Vũ + 3 more
TLDR
This paper introduces "intentmaking," an iterative process for defining experimental goals when mathematicians interact with AI for discovery.
Key contributions
- Identifies "intentmaking" as a new workflow for human-AI collaboration in scientific discovery.
- Describes intentmaking as iteratively discovering, defining, and refining experimental goals with AI.
- Proposes a cycle of intentmaking (defining) and sensemaking (interpreting) in AI-guided research.
- Advocates for designing AI as collaborative instruments, moving beyond simple question/answer models.
Why it matters
This research highlights a crucial, underexplored aspect of human-AI collaboration in scientific discovery. By defining "intentmaking," it provides a framework for designing AI tools that act as true partners, fostering deeper engagement and more effective problem-solving. This shifts the paradigm from AI as a black-box assistant to a collaborative instrument.
Original Abstract
Artificial intelligence offers powerful new tools for scientific discovery, but the interaction paradigms required to effectively harness these systems remain underexplored. In this paper, we present findings from a formative user study with 11 expert mathematicians who used AlphaEvolve, an evolutionary coding agent, to tackle advanced problems in their fields of expertise. We identify and characterize a distinct workflow we term intentmaking, the iterative process of discovering, defining, and refining one's experimental goals through active system interaction. We frame this as a natural extension to sensemaking, the cognitive process of building an understanding of complex or novel data. We suggest that users enter a cycle of intentmaking (defining and updating their experiment) and sensemaking (interpreting the results) which repeats many times during the course of an investigation. Our documentation of these themes suggests an approach to designing AI tools for scientific discovery that goes beyond the existing question/answer model of many current systems, treating them as collaborative instruments rather than opaque black-box assistants.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.