arXiv cs.AI· Yu-Chao Wang, Yanhong Lu, Yingjie Victor Chen, Tim McGraw·· 11 小时前AI 评分26
MAIA：面向艺术委托需求发现的多智能体意图表达系统
MAIA: Multi-Agent Intent Articulation for Requirement Discovery in Art Commissions
AI 导读
MAIA 是一个多智能体系统，通过苏格拉底式提问在"验证优先于发明"规则下帮助委托人把模糊感受转化为可核验的纯文本视觉需求简报。在 N=16 的被试内研究中，完整配置相比最小基线在认知支持上取得显著大幅提升（r = 0.97，p_FDR = 0.003；LMM p_FDR < 0.001）。三名专业概念设计师的探索性盲评还显示，改写后的简报更完整、更易执行。
正文 · 原文
Abstract: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 = 0.97, p_FDR = 0.003; LMM p_FDR < 0.001). Thematic analysis traces the same mechanism, and a validator gate structurally blocks unratified content. An exploratory blind review by three professional concept artists provides complementary descriptive evidence that the rewritten briefs were more complete and executable.
| Comments: | 8 pages, 2 figures. Accepted at AIxHEART 2026 |
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.12097 [cs.HC] |
| (or arXiv:2609.12097v2 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2609.12097 arXiv-issued DOI via DataCite |
Submission history
From: Yu-Chao Wang [view email]
[v1]
Thu, 10 Sep 2026 18:25:21 UTC (466 KB)
[v2]
Wed, 4 Nov 2026 00:54:26 UTC (472 KB)
来源：arXiv cs.AI · arxiv.org