Search papers, labs, and topics across Lattice.
This paper introduces GraphMemix, a novel graph memory framework that optimizes long-term memory organization for multimodal agents by constructing query-aware evidence forests. The approach addresses the limitations of existing methods, which either rely on costly offline summaries or suffer from incomplete context due to naive similarity matching. Experimental results across multiple benchmarks show that GraphMemix significantly enhances memory efficiency and accuracy, establishing a new Pareto frontier in the trade-off between lifecycle cost and performance.
Query-aware evidence forests can drastically reduce memory lifecycle costs while improving accuracy, setting a new standard for multimodal agent memory management.
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.
