@inproceedings{xu-etal-2026-chain,
    title = "Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for {LLM} Agents",
    author = "Xu, Xiucheng  and
      Xu, Bingbing  and
      Xueyun, Tian  and
      Huang, Zihe  and
      Chen, Rongxin  and
      Yunfan, Li  and
      Shen, Huawei",
    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.534/",
    pages = "11618--11631",
    ISBN = "979-8-89176-390-6",
    abstract = "External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive memory construction (e.g., structuring data into graphs) followed by naive retrieval-augmented generation. However, our empirical analysis reveals two fundamental limitations: complex construction incurs high costs with marginal performance gains, and simple context concatenation fails to bridge the gap between retrieval recall and reasoning accuracy. To address above challenges, we propose **CoM (Chain-of-Memory)**, a novel framework that advocates for a paradigm shift toward lightweight construction paired with sophisticated utilization. CoM introduces a *Chain-of-Memory* mechanism that organizes retrieved fragments into coherent inference paths through dynamic evolution, utilizing adaptive truncation to prune irrelevant noise. Extensive experiments on the LongMemEval and LoCoMo benchmarks demonstrate that CoM outperforms strong baselines with accuracy gains of 7.5{\%}{--}10.4{\%}, while drastically reducing computational overhead to approximately 2.7{\%} of token consumption and 6.0{\%} of latency compared to complex memory architectures."
}