Tunable LLM-based Proactive Recommendation Agent

Abstract

Recommender systems are indispensable on various digital platforms. However, traditional methods often reinforce existing user interests, which leads to echo chambers and limits diversity. Proactive Recommendation Systems (PRS) aim to address this issue by cultivating users’ latent interests through multi-step recommendations. Despite advancements, challenges persist particularly in optimizing long-term rewards and adapting to real-time user feedback. In this study, we propose an LLM-based Actor-Critic Agent framework to enhance PRS. This framework utilizes the LLM-based agent to adjust recommendations in real time based on feedback and employs agent-tuning methods to optimize long-term rewards using three proposed reward functions. Extensive experiments validate the significant superiority of this framework over existing methods by optimizing long-term rewards and dynamically evolving with user feedback.

@inproceedings{wang2025tpra,
      title={Tunable LLM-based Proactive Recommendation Agent}, 
      author={Mingze Wang and Chongming Gao and Wenjie Wang and Yangyang Li and Fuli Feng},
      booktitle = "Proceedings of the 63nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
      month = july,
      year = "2025",
      address = "Vienna, Austria",
      publisher = "Association for Computational Linguistics",
      url = "https://openreview.net/forum?id=mcSzLyDsXd#discussion",
}
Copy

Mingze Wang

王铭泽

Chongming Gao

高崇铭 博士后

Wenjie Wang

王文杰 教授

Fuli Feng

冯福利 教授