Open access
Aug 2026
Large Language Model Agents for Recommender Systems: Bridging Behavior and Semantics with Long-Short Term Interest Modeling
This study presents an exploratory LLM-agent-based hybrid recommender system framework, building upon a multi-armed bandit approach, which enables semantic understanding of item content and integrates both short-term and long-term user interaction behaviors for recommendation.
Yiming Cheng, Yi-Tong Ma, Jingyu Wang et al.
· Electronics · 1 citation