@inproceedings{zhang-etal-2026-memsearch,
    title = "{M}em{S}earch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search",
    author = "Zhang, Sheng  and
      Li, Junyi  and
      Zhang, Yingyi  and
      Jia, Pengyue  and
      Wang, Yichao  and
      Qian, Xiaowei  and
      Zhang, Wenlin  and
      Wang, Maolin  and
      Liu, Yong  and
      Zhao, Xiangyu",
    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.41/",
    pages = "925--943",
    ISBN = "979-8-89176-390-6",
    abstract = "Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative think{--}search loop accumulates long system memories, leading to memory dilution problem. In addition, existing memory management methods struggle to capture fine-grained semantic relations between queries and documents and often lose substantial information. Therefore, we propose MemSearch-o1, an agentic search framework built on reasoning-aligned memory growth and retracing. MemSearch-o1 dynamically grows fine-grained memory fragments from memory seed tokens from the queries, then retraces and deeply refines the memory via a contribution function, and finally reorganizes a globally connected memory path. This shifts memory management from stream-like concatenation to structured, token-level growth with path-based reasoning. Experiments on eight benchmark datasets show that MemSearch-o1 substantially mitigates memory dilution, and more effectively activates the reasoning potential of diverse LLMs, establishing a solid foundation for memory-aware agentic intelligence."
}