Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery

2026-05-07

AI Summary

This study investigates how to design effective human-AI interaction paradigms to support expert mathematicians in AI-augmented mathematical discovery. Through qualitative observation of eleven mathematicians employing the evolutionary programming agent AlphaEvolve to tackle cutting-edge problems, the research uncovers a collaborative pattern characterized by iterative cycles between defining experimental objectives and interpreting results. Introducing the concept of “intentmaking” and integrating it with established “sensemaking” processes, the work formulates a cyclic collaboration framework that transcends the limitations of conventional question-answering AI tools. By identifying core interaction mechanisms underlying AI-assisted scientific discovery, this research provides both theoretical grounding and practical guidance for the design of next-generation collaborative AI systems tailored to scientific inquiry.

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.

Problem

• intentmaking
• sensemaking
• human-AI interaction
• scientific discovery
• AI-guided research

Innovation

• intentmaking
• sensemaking
• human-AI collaboration
• scientific discovery
• evolutionary coding agent