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.
This paper presents AIrt Guide, a conversational human-AI system designed to scaffold interpretive curiosity and creative meaning-making during art museum visits. Art engagement is inherently interpretive and creative, and AIrt Guide structures dialogue to support sustained observation, evidence-based reasoning, and elaborative perspective shifting during the act of viewing. Grounded in a mini-c framework of everyday creative cognition, the system implements two pedagogical conversational variations: Visual Thinking Strategies (VTS) and Formal Analysis. Rather than delivering definitive interpretations, the system supports iterative meaning construction while preserving viewer agency and productive ambiguity. Findings from in-person workshops suggest that this form of conversational scaffolding promotes analytic depth and more explicit articulation of visual evidence. Overall, this work demonstrates the potential of conversational AI as a creativity support tool in cultural settings, 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 te reo Māori: mauri, whenua, whanaungatanga, whakapapa, tikanga. The resulting artifacts—both the IT artifacts of code and screen recordings, and the image outputs—form an agentic infrastructure. Māori concepts operate here as computational substrate and philosophical grounding. This poster presents the architecture, the code, and the outputs, and situates the work within Indigenous computational thought.
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 register of artistic interpretation. The Formal Analysis condition was associated with more noun-focused evaluative description and more verb-oriented inquiry framing, while Visual Thinking Strategies (VTS) supported longer, more elaborated responses among participants. These preliminary findings suggest localized differences in how dialogue structure shapes interpretive language, rather than broad shifts in artistic engagement, and point toward design implications for conversational agents deployed in open-ended, interpretive contexts. This work contributes to ongoing questions in museum CUI research about how dialogue design influences user expression and interpretive articulation.
A. Cantrell, Orit Shaer· International Conference on...· 0 citations
Recent discourse around generative artificial intelligence has characterized its implications for creative labor as wholly unprecedented. This article challenges that framing by situating generative A.I. within a longer history of technological change in Hollywood. We conduct a historical analysis of three cases in which an emerging technology promised to automate aspects of creative production: the spread of motorized film projectors in the early 1900s, the rise of computer-based editing software in the mid-1980s, and the introduction of screenwriting software in the late 1980s. Through a content analysis of newspaper and industry trade publications, this analysis finds 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 narratives among workers, management, and the public. Each case is characterized by a different kind of narrative conflict: projectionists fought over the definition of professional skill; film editors confronted accelerated workflows and managerial interference; and screenwriters policed barriers to entry against would-be "hacks." In each of these narrative conflicts, we point to patterned similarities to and differences from contemporary conflicts over generative A.I. in Hollywood.
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 multi-user storytelling. Inspired by Dream of the Red Chamber, the system uses Interactive Audio Augmented Reality (IAAR) to embed narrative logic in embodied action, supported by high-precision tracking and a distributed Wi-Fi audio broadcast architecture. Layered spatial audio and subtle acoustic cues enable strangers to coordinate narrative progression without screens. We discuss how formalizing social rituals as tangible interfaces can support embodied negotiation and collective meaning-making in shared space.
Limeng Wang, Yuan Yao, Zhihao Yao et al.· Creativity & Cognition· 0 citations
