C3M：面向长时程任务的跨会话多模态记忆维护
C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
- Huzhou Normal University（湖州师范学院）
- Alibaba Group（阿里巴巴集团）
- University of Waterloo（滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
C3M提出跨会话多模态记忆组织，通过有界活跃索引和关系感知更新，在受限预算下保留并恢复证据，支持长时程任务推理。
中文摘要 AI 辅助
长时程任务要求在受限且查询盲的记忆预算下，保留并随后恢复跨会话的证据。现有的压缩方法可能丢弃细粒度的视觉线索，或混淆语义相似但不兼容的观察结果。我们提出C3M，一种跨会话多模态记忆组织方法，它在持久化的源文本-图像证据上维护一个有界的活跃索引。关系感知的更新在保留互补和不兼容记录的同时，整合了安全的冗余。在查询时，预算路由选择有用的索引页，并在固定的读取器预算下扩展其关联的源证据。这些机制共同建立了一种紧凑且保留来源的跨会话长时程任务多模态记忆组织，保留了可靠下游推理所需的时间区分和来源链接。代码可在以下URL获取。
英文摘要
Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy while preserving complementary and incompatible records. At query time, budgeted routing selects useful index pages and expands their associated source evidence under a fixed reader budget. Together, these mechanisms establish a compact, provenance-preserving multimodal memory organization for cross-session long-horizon tasks, retaining temporal distinctions and source links required for reliable downstream reasoning. Code is available at https://github.com/HuzhouNLP/C3M.
