fCrit: A Visual Explanation System for Furniture Design Creative Support

2025-08-17

AI Summary

This study addresses the limited explainability and poor user adaptability of AI in creative design. We propose fCrit, a conversational, explainable critique system tailored for furniture design. fCrit employs a multi-agent architecture integrating a structured design knowledge base, natural language understanding, and vision-grounded explanation generation, augmented by reflective learning and formal design analysis to dynamically produce personalized, visually grounded feedback aligned with designers’ linguistic conventions and cognitive frameworks. Its key contribution lies in being the first to deeply embed explainable AI within the artistic creation loop—ensuring transparent reasoning and context-aware, interactive critique. User studies demonstrate that fCrit significantly improves designers’ comprehension, acceptance, and engagement with AI-generated feedback, establishing a novel human-centered paradigm for creative assistance. (149 words)

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Agentic search

Abstract

We introduce fCrit, a dialogue-based AI system designed to critique furniture design with a focus on explainability. Grounded in reflective learning and formal analysis, fCrit employs a multi-agent architecture informed by a structured design knowledge base. We argue that explainability in the arts should not only make AI reasoning transparent but also adapt to the ways users think and talk about their designs. We demonstrate how fCrit supports this process by tailoring explanations to users' design language and cognitive framing. This work contributes to Human-Centered Explainable AI (HCXAI) in creative practice, advancing domain-specific methods for situated, dialogic, and visually grounded AI support.

Problem

• Critique furniture designs with explainable AI
• Adapt AI explanations to designers' language
• Support creative practice via dialogic visual AI

Innovation

• Dialogue-based AI for design critique
• Multi-agent architecture with knowledge base
• Tailored explanations using user's design language