@inproceedings{xu-etal-2026-structmem,
    title = "{S}truct{M}em: Structured Memory for Long-Horizon Behavior in {LLM}s",
    author = "Xu, Buqiang  and
      Chen, Yijun  and
      Fang, Jizhan  and
      Zhong, Ruobin  and
      Yao, Yunzhi  and
      Zhu, Yuqi  and
      Du, Lun  and
      Deng, Shumin",
    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 2: Short 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-short.12/",
    pages = "122--146",
    ISBN = "979-8-89176-391-3",
    abstract = "Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose StructMem, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on LoCoMo, while substantially reducing token usage, API calls, and runtime compared to prior memory systems."
}