@inproceedings{peng-etal-2025-survey,
    title = "A Survey on {LLM}-powered Agents for Recommender Systems",
    author = "Peng, Qiyao  and
      Liu, Hongtao  and
      Huang, Hua  and
      Yang, Jian  and
      Yang, Qing  and
      Shao, Minglai",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.620/",
    doi = "10.18653/v1/2025.findings-emnlp.620",
    pages = "11574--11583",
    ISBN = "979-8-89176-335-7",
    abstract = "Recently, Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation, prompting the recommendation community to leverage these powerful models to address fundamental challenges in traditional recommender systems, including limited comprehension of complex user intents, insufficient interaction capabilities, and inadequate recommendation interpretability. This survey presents a comprehensive synthesis of this rapidly evolving field. We consolidate existing studies into three paradigms: (i) recommender-oriented methods, which directly enhance core recommendation mechanisms; (ii) interaction-oriented methods, which conduct multi-turn conversations to elicit preferences and deliver interpretable explanations; and (iii) simulation-oriented methods, that model user-item interactions through multi-agent frameworks. Then, we dissect a four-module agent architecture: profile, memory, planning, and action. Then we review representative designs, public datasets, and evaluation protocols. Finally, we give the open challenges that impede real-world deployment, including cost-efficient inference, robust evaluation, and security."
}