@inproceedings{wang-etal-2026-streammeco,
    title = "{S}tream{M}e{C}o: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding",
    author = "Wang, Junxi  and
      Sun, Te  and
      Zhu, Jiayi  and
      Li, Junxian  and
      Xu, Haowen  and
      Wen, Zichen  and
      Hu, Xuming  and
      li, Zhiyu  and
      Zhang, Linfeng",
    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.647/",
    pages = "13234--13251",
    ISBN = "979-8-89176-395-1",
    abstract = "Vision agent memory has shown remarkable effectiveness in long-video understanding; however, storing such memory for videos incurs substantial overhead, leading to high costs in both storage and computation. To address this issue, we propose StreamMeCo, an efficient Stream Agent Memory Compression framework. Specifically, based on the connectivity of the memory graph, StreamMeCo introduces edge-free minmax sampling for isolated nodes and edge-aware weight pruning for connected nodes, evicting redundant memory nodes while maintaining accuracy. In addition, we introduce a time-decay memory retrieval mechanism to mitigate the performance degradation caused by memory compression. Extensive experiments on three challenging benchmark datasets (M3-Bench-robot, M3-Bench-web, and Video-MME-Long) demonstrate that under 70{\%} memory graph compression, StreamMeCo achieves a 1.87{\texttimes} speedup in memory retrieval while delivering an average accuracy improvement of 1.0{\%}. Our code is available at https://github.com/Celina-love-sweet/StreamMeCo."
}