Saved in:
Bibliographic Details
Main Authors: Ma, Hongbo, Shen, Fei, Xu, Hongbin, Wang, Xiaoce, Xu, Gang, Zheng, Jinkai, Qu, Liangqiong, Li, Ming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.06555
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912532785004544
author Ma, Hongbo
Shen, Fei
Xu, Hongbin
Wang, Xiaoce
Xu, Gang
Zheng, Jinkai
Qu, Liangqiong
Li, Ming
author_facet Ma, Hongbo
Shen, Fei
Xu, Hongbin
Wang, Xiaoce
Xu, Gang
Zheng, Jinkai
Qu, Liangqiong
Li, Ming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06555
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback
Ma, Hongbo
Shen, Fei
Xu, Hongbin
Wang, Xiaoce
Xu, Gang
Zheng, Jinkai
Qu, Liangqiong
Li, Ming
Computer Vision and Pattern Recognition
Computers and Society
Multiagent Systems
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.
title StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback
topic Computer Vision and Pattern Recognition
Computers and Society
Multiagent Systems
url https://arxiv.org/abs/2508.06555