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

arXiv: https://arxiv.org/abs/2605.05921 · HTML: https://mlsanity.com/paper/2605.05921/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 41 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 11 of 11)

- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients](https://mlsanity.com/paper/1912.04871/) (2019)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [Mathematical exploration and discovery at scale](https://mlsanity.com/paper/2511.02864/) (2025)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [Cocoa: Co-Planning and Co-Execution with AI Agents](https://mlsanity.com/paper/2412.10999/) (2024)
- [Interactive AI Alignment: Specification, Process, and Evaluation Alignment](https://mlsanity.com/paper/2311.00710/) (2023)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineering](https://mlsanity.com/paper/2411.06099/) (2024)
- [Evolving Ranking Functions for Canonical Blow-Ups in Positive Characteristic](https://mlsanity.com/paper/2602.06553/) (2026)

## Built on by (most cited first, 1 of 1)

- [Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks](https://mlsanity.com/paper/2606.01975/) (2026)

## Abstract (arXiv)

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.