用图结构动态构建与查询相关的记忆森林，提升多模态长时记忆效率。
GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory
- 将记忆组织为查询感知的证据森林，通过图优化选择相关子图。
- 在4个基准上超越现有方法，精度提升且生命周期成本更低。
- 适合需要高效长时记忆的多模态智能体系统研发者。
多模态智能体的长期记忆组织仍具挑战性，因现有方法或依赖昂贵的非查询感知离线摘要，或采用简单的嵌入相似性匹配，导致上下文不完整且冗余。为此，我们提出GraphMemix，一种组合优化的图内存框架，将记忆组织建模为查询感知的证据森林构建。具体包含三个核心组件：(1) 候选图构建，通过模式与语义关系扩展多视角种子记忆，获取查询感知的原始上下文；(2) 证据效用与激活成本，解耦直接记忆支持与锚点条件关系验证，抑制冗余或冲突信息；(3) 森林优化，在最大证据预算下联合选择具备可靠关系结构的森林格式记忆上下文。通过将记忆组织为查询相关的子图，该方法避免了高昂的生命周期开销，并恢复低相似度互补证据。在四个长期多模态记忆基准上的实验表明，该方法在不同基础模型下均显著提升性能，建立了准确率与生命周期成本间的全新帕累托前沿。
原文摘要 · Abstract (English)
Organizing long-term memory for multimodal agents remains challenging because existing methods either suffer from expensive question-agnostic offline summaries or naive embedding similarity matching that introduces incomplete and redundant context. To address these issues, we propose GraphMemix, a combinatorial-optimization graph memory framework that models memory organization as query-aware evidence-forest construction. Specifically, our method consists of three key components:(1) candidate graph construction, which expands multi-view seed memories through schema and semantic relations to acquire query-aware original context; (2) evidence utility and activation costs, which decouples direct memory support from anchor-conditioned relation verification to suppress redundant or conflicting information; and (3) forest optimization, which jointly selects a forest-format memory context under a maximum evidence budget and its reliable relational structure. By organizing memory into a query-relevant subgraph, the method avoids substantial lifecycle cost and recovers low-similarity complementary evidence. Experimental results across four long-term multimodal memory benchmarks demonstrate significant improvements with different foundation models and establish a new Pareto frontier between accuracy and lifecycle cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。