@inproceedings{lian-etal-2026-verbatim,
    title = "From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents",
    author = "Lian, Niu  and
      Wang, Yuting  and
      Yao, Hanshu  and
      Wang, Jinpeng  and
      Chen, Bin  and
      Wang, Yaowei  and
      Zhang, Min  and
      Xia, Shu-Tao",
    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.533/",
    pages = "11601--11617",
    ISBN = "979-8-89176-390-6",
    abstract = "While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extremes: vision-centric methods that incur high latency and redundancy through dense visual accumulation, or text-centric approaches that suffer from detail loss and hallucination via aggressive captioning. To bridge this gap, we propose **MM-Mem**, a pyramidal multimodal memory architecture grounded in *Fuzzy-Trace Theory*. **MM-Mem** structures memory hierarchically into a *Sensory Buffer*, *Episodic Stream*, and *Symbolic Schema*, enabling the progressive distillation of fine-grained perceptual traces (*verbatim*) into high-level semantic schemas (*gist*).Furthermore, to govern the dynamic construction of memory, we derive a Semantic Information Bottleneck objective and introduce SIB-GRPO to optimize the trade-off between memory compression and task-relevant information retention.In inference, we design an entropy-driven top-down memory retrieval strategy.Extensive experiments across 4 benchmarks confirm that **MM-Mem** achieves state-of-the-art performance on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.Code and associated configurations are publicly available at `https://github.com/EliSpectre/MM-Mem{`}."
}