Agentic Personalized Fashion Recommendation in the Age of Generative AI: Challenges, Opportunities, and Evaluation

TL;DR

This paper discusses the challenges faced by modern fashion recommender systems and proposes an innovative agentic mixed-modality refinement pipeline that enhances adaptability and stakeholder engagement in fashion recommendations.

Contribution

It introduces the Agentic Mixed-Modality Refinement (AMMR) pipeline, integrating multimodal encoders, LLM planners, and dynamic retrieval for improved fashion recommendation systems.

Findings

AMMR effectively combines image and text references for personalized recommendations.

The proposed system adapts to fast-changing fashion inventories and user preferences.

Moving beyond static retrieval improves user satisfaction and reduces return rates.

Abstract

Fashion recommender systems (FaRS) face distinct challenges due to rapid trend shifts, nuanced user preferences, intricate item-item compatibility, and the complex interplay among consumers, brands, and influencers. Traditional recommendation approaches, largely static and retrieval-focused, struggle to effectively capture these dynamic elements, leading to decreased user satisfaction and elevated return rates. This paper synthesizes both academic and industrial viewpoints to map the distinctive output space and stakeholder ecosystem of modern FaRS, identifying the complex interplay among users, brands, platforms, and influencers, and highlighting the unique data and modeling challenges that arise. We outline a research agenda for industrial FaRS, centered on five representative scenarios spanning static queries, outfit composition, and multi-turn dialogue, and argue that mixed-modality refinement-the ability to combine image-based references (anchors) with nuanced textual constraints-is a particularly critical task for real-world deployment. To this end, we propose an Agentic Mixed-Modality Refinement (AMMR) pipeline, which fuses multimodal encoders with agentic LLM planners and dynamic retrieval, bridging the gap between expressive user intent and fast-changing fashion inventories. Our work shows that moving beyond static retrieval toward adaptive, generative, and stakeholder-aware systems is essential to satisfy the evolving expectations of fashion consumers and brands.