Sanyu Studio is presented, a multi-agent dialogue system that models 321 Sanyu oil paintings as agents with fact, interpretation, organization, and memory-filtering mechanisms that suggest that, under conditions of limited historical evidence, AI can amplify human agency and offer public audiences an interactive entry point into art-historical interpretation.
Abstract
Amid concerns that generative AI may standardize art interpretation, this paper examines whether LLM-based interaction can support plural art-historical narrative construction. We present Sanyu Studio, a multi-agent dialogue system that models 321 Sanyu oil paintings as agents with fact, interpretation, organization, and memory-filtering mechanisms. Based on a seven-day workshop with eight art-university participants, the study shows that user prompts, evidence organization, and cognitive tendencies shaped divergent yet coherent versions of digital Sanyu. The findings suggest that, under conditions of limited historical evidence, AI can amplify human agency and offer public audiences an interactive entry point into art-historical interpretation.
The potential of conversational AI as a creativity support tool in cultural settings is demonstrated, augmenting everyday interpretive practice by expanding associative space without resolving meaning.
A. Cantrell, Orit Shaer· Creativity & Cognition· 0 citations
Agentic Images is a rule-based multi-agent drawing engine in which autonomous agents carry source works into a shared canvas and negotiate territory frame by frame. There is no training corpus, no large language model, no diffusion. The claim of agency is through the piece’s conceptual architecture which is written in...
The study contributes a cautious comparative framework for distinguishing prompt-induced structural conformity from analytically emergent features in AI-generated narrative.
This paper presents the AIrt Guide, a flipped-interaction museum learning tool, as a comparative lens on how conversational design shapes interpretive articulation. We report preliminary findings from a study with n = 24 participants, focusing specifically on how these conversational structures shape the linguistic reg...
A. Cantrell, Orit Shaer· International Conference on...· 0 citations
A historical analysis of three cases in which an emerging technology promised to automate aspects of creative production and found that whether and how a technology is understood as "automating" by different sets of actors is not simply a technical determination but a culturally constructed one, shaped by competing nar...
Caitlin Petre, Julia Ticona· AI & SOCIETY· 0 citations
Contemporary immersive theatre often limits audience agency to passive observation or spatial navigation, leaving social co-presence underdesigned. We present The Banquet, a co-located participatory sound theatre that turns culturally grounded ritual gestures—raising and clinking cups—into an interaction grammar for mu...
Limeng Wang, Yuan Yao, Zhihao Yao et al.· Creativity & Cognition· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
