Tunable LLM-based Proactive Recommendation Agent
Mingze Wang, Chongming Gao, Wenjie Wang, Yangyang Li, Fuli Feng
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.
BibTeX
@inproceedings{wang-etal-2025-tunable,
title = "Tunable {LLM}-based Proactive Recommendation Agent",
author = "Wang, Mingze and
Gao, Chongming and
Wang, Wenjie and
Li, Yangyang and
Feng, Fuli",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.944/",
doi = "10.18653/v1/2025.acl-long.944",
pages = "19262--19276",
ISBN = "979-8-89176-251-0"
}