From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents

TL;DR

The paper discusses a paradigm shift in recommender systems driven by LLM agents, emphasizing transparent, inspectable, and governable user representations over traditional hidden profiling methods.

Contribution

It introduces a new framework for personalization that prioritizes user control, interpretability, and cross-platform portability in the era of LLM-mediated interactions.

Findings

Proposes a shift to governable personalization with inspectable user models.

Identifies five interconnected research fronts for future recommender systems.

Highlights the importance of user understanding and control in personalization.

Abstract

Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-based assistants increasingly mediate search, shopping, travel, and content access, this arrangement may be giving way to a new personalization stack in which user representation is no longer confined to isolated platforms. In this paper, we argue that the key issue is not simply that large language models can enhance recommendation quality, but that they reconfigure where and how user representations are produced, exposed, and acted upon. We propose a shift from hidden platform profiling toward governable personalization, where user representations may become more inspectable, revisable, portable, and consequential across services. Building on this view, we identify five research fronts for recommender systems: transparent yet privacy-preserving user modeling, intent translation and alignment, cross-domain representation and memory design, trustworthy commercialization in assistant-mediated environments, and operational mechanisms for ownership, access, and accountability. We position these not as isolated technical challenges, but as interconnected design problems created by the emergence of LLM agents as intermediaries between users and digital platforms. We argue that the future of recommender systems will depend not only on better inference, but on building personalization systems that users can meaningfully understand, shape, and govern.