Saved in:
Bibliographic Details
Main Authors: Shen, Chenglei, Zhan, Yi, Yu, Weijie, Zhang, Xiao, Xu, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.08067
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908820566966272
author Shen, Chenglei
Zhan, Yi
Yu, Weijie
Zhang, Xiao
Xu, Jun
author_facet Shen, Chenglei
Zhan, Yi
Yu, Weijie
Zhang, Xiao
Xu, Jun
contents In real-world streaming recommender systems, user preferences evolve dynamically over time. Existing bandit-based methods treat time merely as a timestamp, neglecting its explicit relationship with user preferences and leading to suboptimal performance. Moreover, online learning methods often suffer from inefficient exploration-exploitation during the early online phase. To address these issues, we propose HyperBandit+, a novel contextual bandit policy that integrates a time-aware hypernetwork to adapt to time-varying user preferences and employs a large language model-assisted warm-start mechanism (LLM Start) to enhance exploration-exploitation efficiency in the early online phase. Specifically, HyperBandit+ leverages a neural network that takes time features as input and generates parameters for estimating time-varying rewards by capturing the correlation between time and user preferences. Additionally, the LLM Start mechanism employs multi-step data augmentation to simulate realistic interaction data for effective offline learning, providing warm-start parameters for the bandit policy in the early online phase. To meet real-time streaming recommendation demands, we adopt low-rank factorization to reduce hypernetwork training complexity. Theoretically, we rigorously establish a sublinear regret upper bound that accounts for both the hypernetwork and the LLM warm-start mechanism. Extensive experiments on real-world datasets demonstrate that HyperBandit+ consistently outperforms state-of-the-art baselines in terms of accumulated rewards.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08067
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations
Shen, Chenglei
Zhan, Yi
Yu, Weijie
Zhang, Xiao
Xu, Jun
Machine Learning
In real-world streaming recommender systems, user preferences evolve dynamically over time. Existing bandit-based methods treat time merely as a timestamp, neglecting its explicit relationship with user preferences and leading to suboptimal performance. Moreover, online learning methods often suffer from inefficient exploration-exploitation during the early online phase. To address these issues, we propose HyperBandit+, a novel contextual bandit policy that integrates a time-aware hypernetwork to adapt to time-varying user preferences and employs a large language model-assisted warm-start mechanism (LLM Start) to enhance exploration-exploitation efficiency in the early online phase. Specifically, HyperBandit+ leverages a neural network that takes time features as input and generates parameters for estimating time-varying rewards by capturing the correlation between time and user preferences. Additionally, the LLM Start mechanism employs multi-step data augmentation to simulate realistic interaction data for effective offline learning, providing warm-start parameters for the bandit policy in the early online phase. To meet real-time streaming recommendation demands, we adopt low-rank factorization to reduce hypernetwork training complexity. Theoretically, we rigorously establish a sublinear regret upper bound that accounts for both the hypernetwork and the LLM warm-start mechanism. Extensive experiments on real-world datasets demonstrate that HyperBandit+ consistently outperforms state-of-the-art baselines in terms of accumulated rewards.
title Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations
topic Machine Learning
url https://arxiv.org/abs/2602.08067