# MAIA: Multi-Agent Intent Articulation for Requirement Discovery in Art Commissions

arXiv: https://arxiv.org/abs/2609.12097 · HTML: https://mlsanity.com/paper/2609.12097/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen](https://mlsanity.com/paper/2005.00701/) (2020)
- [Designing Participatory AI: Creative Professionals' Worries and Expectations about Generative AI](https://mlsanity.com/paper/2303.08931/) (2023)
- [Exploring the Collaborative Co-Creation Process with AI: A Case Study in Novice Music Production](https://mlsanity.com/paper/2501.15276/) (2025)
- [A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts](https://mlsanity.com/paper/2410.11877/) (2024)
- [Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon Explanations](https://mlsanity.com/paper/2503.00715/) (2025)
- [HAIGEN: Towards Human-AI Collaboration for Facilitating Creativity and Style Generation in Fashion Design](https://mlsanity.com/paper/2408.00855/) (2024)

## Abstract (arXiv)

In bespoke art commissions, laypeople know what they feel but lack the words to specify it: one participant wanted a laid-off truck driver depicted as "a ghost in his own machine" but left the medium, scale, and palette unsaid. We frame this as an articulation bottleneck at an under-served upstream stage: requirement discovery, which precedes any artist or image generator and forces the commissioner to constitute intent in the first place. We present MAIA (Multi-Agent Intent Articulation), a multi-agent system that scaffolds this stage through Socratic inquiry under a "Verification over Invention" rule, turning vague affect into a text-only brief of visual terms the user verifies. In a within-subjects study (N = 16), the full configuration produced a large, significant gain in Cognitive Support over a minimal baseline (r = 0.96, p_FDR = 0.015; LMM p_FDR < 0.001). Thematic analysis traces the same mechanism, and a validator gate structurally blocks unratified content. A complementary blind review by three professional concept artists on a sampled set of briefs corroborates this improvement from the artist's side: AI rewriting improved visual completeness and executability in all eight sampled tasks (task-level Wilcoxon p = 0.008; FDR q = 0.010), with directionally larger gains under MAIA than under the baseline (underpowered, d = 1.4-2.6).