cs.CLNov 9, 2026

HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents

Authors: Haozhen Zhang, Bohan Liu, Jianzhu Bao, Qingyuan Liu, Haodong Yue, Xiao Li, Zi Pong Lim, Wenya Wang

Organizations: Nanyang Technological University · Tsinghua University · Sun Yat-sen University · Aumovio Singapore Pte. Ltd.

Abstract

As multimodal agents accumulate increasingly long interaction histories, effectively retrieving and utilizing past information becomes critical for long-term interaction. Existing memory systems typically rely on semantic retrieval over compressed memories and expose predefined representations, which may miss relevant memories and overlook heterogeneous evidence needs across queries. We introduce \hivemem, a multimodal memory framework that interleaves Horizontal Memory Expansion with Vertical Evidence Composition. For horizontal memory expansion, \hivemem organizes memory episodes into a relational graph using textual and visual anchors, expanding semantically retrieved seeds with related neighbors to recover complementary information. For vertical evidence composition, each retrieved memory retains multiple evidence forms, including compact summaries, captions, grounded visual views, raw images, and interaction history. A lightweight trainable selector independently composes an evidence subset for each retrieved memory, enabling query-adaptive utilization of heterogeneous multimodal information. This two-dimensional design jointly broadens memory coverage and adapts the evidence contributed by individual memories. Experiments across three multimodal memory benchmarks show that \hivemem consistently improves task performance across base models while reducing token consumption by about 90% compared with the most efficient competing multimodal baselines.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents

    Aug 2, 2026Jingyu Sun, Yan Lin, Yuyang Xue +10Memory-Augmented VLMsMultimodal Memory

  2. GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory

    Aug 27, 2026Geng Li, Yuhao Wang, Dong Li +2Multimodal MemoryAgent Memory Management

  3. MEMO: Multimodal Evidence Memory Organization for Long-Horizon LLM Agents

    Sep 7, 2026Xian Gao, Jinpeng Wang, Jiacheng Ruan +3Multimodal MemoryLong-Horizon LLM Agents