@inproceedings{huang-etal-2026-controllable,
    title = "Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human{--}Agent Interaction",
    author = "Huang, Zisu  and
      Tian, Muzhao  and
      Wang, Xiaohua  and
      Xu, Jingwen  and
      Guo, Zhengkang  and
      Qian, Qi  and
      Song, Kaitao  and
      Yuan, Jiakang  and
      Lv, Changze  and
      Zheng, Xiaoqing",
    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.670/",
    pages = "14699--14719",
    ISBN = "979-8-89176-390-6",
    abstract = "As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to Memory Anchoring, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent{'}s reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose Steerable Memory Agent, SteeM, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration."
}