@inproceedings{zhang-etal-2026-memory,
    title = "Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks",
    author = "Zhang, Yuxiang  and
      Shu, Jiangming  and
      Ma, Ye  and
      Lin, Xueyuan  and
      Wu, Shangxi  and
      Sang, Jitao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.956/",
    pages = "19149--19164",
    ISBN = "979-8-89176-395-1",
    abstract = "Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness of the agent{'}s reasoning state, leading to suboptimal decisions. We propose Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions. By formulating context management as in-place editing operations (deletion, insertion), MemAct enables joint optimization of information retention and task performance through end-to-end reinforcement learning. To address the computational challenges of dynamic context updates, we introduce Dynamic Context Policy Optimization, which restores training efficiency without compromising reasoning integrity. Experiments show that MemAct-RL-14B matches the accuracy of models 16{\texttimes} larger while reducing average context length by 51{\%}, with learned strategies that adapt to model capabilities and generalize across task complexities. The code and datasets are available at https://github.com/ADaM-BJTU/MemAct."
}