@inproceedings{wang-etal-2026-shopsimulator,
    title = "{S}hop{S}imulator: Evaluating and Exploring {RL}-Driven {LLM} Agent for Shopping Assistants",
    author = "Wang, Pei  and
      Wu, Yanan  and
      Song, Xiaoshuai  and
      Wang, Weixun  and
      Chen, Gengru  and
      Li, Zhongwen  and
      Yan, Kezhong  and
      Liu, Qi  and
      Deng, Ken  and
      Zhao, Shuaibing  and
      Xiong, Shaopan  and
      Liu, Xuepeng  and
      Chen, Xuefeng  and
      Deng, Wanxi  and
      Su, Wenbo  and
      Zheng, Bo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1647/",
    pages = "35600--35619",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret personal preferences, engage in multi-turn dialogues, and ultimately retrieve and discriminate among highly similar products. However, existing research has yet to provide a unified simulation environment that consistently captures all of these aspects, and always focuses solely on evaluation benchmarks without training support. In this paper, we introduce ShopSimulator, a large-scale and challenging Chinese shopping environment. Leveraging ShopSimulator, we evaluate LLMs across diverse scenarios, finding that even the best-performing models achieve less than 40{\%} full-success rate. Error analysis reveals that agents struggle with deep search and product selection in long trajectories, fail to balance the use of personalization cues, and to effectively engage with users. Further training exploration provides practical guidance for overcoming these weaknesses, with the combination of supervised fine-tuning (SFT) and reinforcement learning (RL) yielding significant performance improvements."
}