English

Deep Research for Recommender Systems

Information Retrieval 2026-03-10 v1

Abstract

The technical foundations of recommender systems have progressed from collaborative filtering to complex neural models and, more recently, large language models. Despite these technological advances, deployed systems often underserve their users by simply presenting a list of items, leaving the burden of exploration, comparison, and synthesis entirely on the user. This paper argues that this traditional "tool-based" paradigm fundamentally limits user experience, as the system acts as a passive filter rather than an active assistant. To address this limitation, we propose a novel deep research paradigm for recommendation, which replaces conventional item lists with comprehensive, user-centric reports. We instantiate this paradigm through RecPilot, a multi-agent framework comprising two core components: a user trajectory simulation agent that autonomously explores the item space, and a self-evolving report generation agent that synthesizes the findings into a coherent, interpretable report tailored to support user decisions. This approach reframes recommendation as a proactive, agent-driven service. Extensive experiments on public datasets demonstrate that RecPilot not only achieves strong performance in modeling user behaviors but also generates highly persuasive reports that substantially reduce user effort in item evaluation, validating the potential of this new interaction paradigm.

Keywords

Cite

@article{arxiv.2603.07605,
  title  = {Deep Research for Recommender Systems},
  author = {Kesha Ou and Chenghao Wu and Xiaolei Wang and Bowen Zheng and Wayne Xin Zhao and Weitao Li and Long Zhang and Sheng Chen and Ji-Rong Wen},
  journal= {arXiv preprint arXiv:2603.07605},
  year   = {2026}
}

Comments

24 pages, 5 figures, 5 tables

R2 v1 2026-07-01T11:09:07.425Z