Sanyu Studio: A Multi-Agent System for Art-Historical Narrative Construction
Summary
This paper introduces Sanyu Studio, a multi-agent dialogue system that uses LLMs to construct art-historical narratives for Sanyu oil paintings, showing how AI can support diverse interpretations through user interactions.
View Cached Full Text
Cached at: 08/20/26, 10:18 AM
# Sanyu Studio: A Multi-Agent System for Art-Historical Narrative Construction Source: [https://arxiv.org/abs/2608.18677](https://arxiv.org/abs/2608.18677) [View PDF](https://arxiv.org/pdf/2608.18677) > 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\. ## Submission history From: Hongye Yang \[[view email](https://arxiv.org/show-email/55eea45f/2608.18677)\] **\[v1\]**Wed, 19 Aug 2026 08:28:38 UTC \(2,018 KB\)
Similar Articles
@SuJinyan6: https://x.com/SuJinyan6/status/2073955240349770069
This blog post by SuJinyan6 examines the evolution of AI agents from simple LLM+tool use to context engineering and long-running harnesses, citing Anthropic's recent work and discussing how agent capability is now a system-level property involving multiple components.
YeasierAgent: Agentic Social Sandbox as a Canvas for Intent-Driven Creation of Platform-Agnostic Symbiotic Agent-Native Applications
This paper introduces YeasierAgent, a paradigm for building platform-agnostic, agent-native applications that replace traditional GUI-based apps with immersive, intent-driven experiences based on symbiotic agents and narrative worlds.
Investigating Multi-Agent Deliberation in Law
This paper investigates multi-agent deliberation methods for legal reasoning tasks using LLMs, introducing two novel frameworks inspired by courtroom procedures. The experiments show that multi-agent systems achieve comparable overall performance to monolithic LLMs but produce distinct answers and can solve cases that baselines fail, highlighting the potential of multi-agent approaches for legal AI.
Experiments in Agentic AI for Science
This paper presents two agentic AI frameworks, DeepTS/DeepCollector and DeepScribe, that automate scientific workflows including time-series data curation and conversion of physics lectures into structured reports, using a hybrid local-cloud architecture with LLMs.
LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching
LectūraAgents is a multi-agent framework for adaptive personalized learning that mimics professor-student interactions and generates embodied teaching actions aligned with learner profiles. It introduces a hierarchical architecture, an adaptive embodied teaching mechanism, and a Teaching Action-Speech Alignment algorithm, showing consistent improvements over existing approaches.