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

• URL: http://arxiv.org/abs/2604.20065v1
• Date: Wed, 22 Apr 2026 00:04:47 GMT
• Title: From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
• Abstract summary: We argue that the key issue is not simply that large language models can enhance recommendation quality, but that they mediate where and how user representations are produced, exposed, and acted upon.<n>We propose a shift from hidden platform profiling toward governable personalization, where user representations may become more inspectable, revisable, portable, and consequential across services.
• Score: 44.20821259751986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries [44.615224255419484]
  We argue for a shift from platform-centric personalization to user-governed personalization.<n>The key asymmetry lies in data access: only users can aggregate their own cross-platform and offline information.<n>We provide proof-of-concept evidence that users equipped with cross-platform data exports and an off-the-shelf LLM agent can outperform single-platform personalization baselines.
  arXiv  Detail & Related papers  (2026-05-10T22:31:59Z)
• The Next Paradigm Is User-Centric Agent, Not Platform-Centric Service [44.35361893379857]
  This paper argues that the future of digital services should shift from a platform-centric to a user-centric agent.<n>User-centric agents prioritize privacy, align with user-defined goals, and grant users control over their preferences and actions.
  arXiv  Detail & Related papers  (2026-02-17T16:07:44Z)
• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time [87.99027488664282]
  PersonaAgent is a framework designed to address versatile personalization tasks.<n>It integrates a personalized memory module and a personalized action module.<n>Test-time user-preference alignment strategy ensures real-time user preference alignment.
  arXiv  Detail & Related papers  (2025-06-06T17:29:49Z)
• Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs) [7.71667852309443]
  System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour.<n>LLMs deployers increasingly use them to ensure consistent responses across contexts.<n>As system prompts become more complex, they can directly or indirectly introduce unaccounted for side effects.
  arXiv  Detail & Related papers  (2025-05-27T12:19:08Z)
• Creating General User Models from Computer Use [53.59999173952482]
  This paper presents an architecture for a general user model (GUM) that learns about you by observing any interaction you have with your computer.<n>The GUM takes as input any unstructured observation of a user (e.g., device screenshots) and constructs confidence-weighted propositions that capture user knowledge and preferences.
  arXiv  Detail & Related papers  (2025-05-16T04:00:31Z)
• iAgent: LLM Agent as a Shield between User and Recommender Systems [33.289547118795674]
  recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.<n>We propose a new user-agent-platform paradigm, where agent serves as the protective shield between user and recommender system.
  arXiv  Detail & Related papers  (2025-02-20T15:58:25Z)
• Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem [55.21502268698577]
  This work investigates the task of unsupervised model personalization, adapted to continually evolving, unlabeled local user images. We provide a novel Dual User-Adaptation framework (DUA) to explore the problem. This framework flexibly disentangles user-adaptation into model personalization on the server and local data regularization on the user device.
  arXiv  Detail & Related papers  (2020-03-30T09:35:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.