StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback

2025-08-06

AI Summary

Current intelligent fashion systems lack a unified framework integrating personalized design, recommendation, virtual try-on, and aesthetic evaluation, resulting in suboptimal outfit coherence and artistic quality. To address this, we propose the first collaborative multi-agent framework featuring dual specialized roles—Designer and Advisor—operating in a closed-loop system. Our method introduces a novel negative-feedback-driven iterative optimization paradigm grounded in a hierarchical vision-language model (VLM): it generates fine-grained negative prompts from multi-scale negative samples to enable precise alignment—from individual garments to full ensembles. The framework jointly incorporates personalized recommendation, physics-aware virtual try-on, and multidimensional aesthetic assessment. Experiments demonstrate significant improvements over state-of-the-art baselines across style consistency, visual realism, and expert-rated artistic quality, establishing a new performance benchmark for intelligent fashion systems.

Technology Category

• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Intelligent User Interfaces

Application Category

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

Abstract

The advancement of intelligent agents has revolutionized problem-solving across diverse domains, yet solutions for personalized fashion styling remain underexplored, which holds immense promise for promoting shopping experiences. In this work, we present StyleTailor, the first collaborative agent framework that seamlessly unifies personalized apparel design, shopping recommendation, virtual try-on, and systematic evaluation into a cohesive workflow. To this end, StyleTailor pioneers an iterative visual refinement paradigm driven by multi-level negative feedback, enabling adaptive and precise user alignment. Specifically, our framework features two core agents, i.e., Designer for personalized garment selection and Consultant for virtual try-on, whose outputs are progressively refined via hierarchical vision-language model feedback spanning individual items, complete outfits, and try-on efficacy. Counterexamples are aggregated into negative prompts, forming a closed-loop mechanism that enhances recommendation quality.To assess the performance, we introduce a comprehensive evaluation suite encompassing style consistency, visual quality, face similarity, and artistic appraisal. Extensive experiments demonstrate StyleTailor's superior performance in delivering personalized designs and recommendations, outperforming strong baselines without negative feedback and establishing a new benchmark for intelligent fashion systems.

Problem

• Personalized fashion styling lacks intelligent solutions
• Unified framework for design, recommendation, try-on, evaluation
• Iterative refinement via hierarchical negative feedback needed

Innovation

• Hierarchical negative feedback for adaptive refinement
• Collaborative agent framework for fashion styling
• Vision-language model for personalized recommendations