章节结构(全文标题提取): Related Work MemFuseBench MemFuse Experiments Conclusion
📊 结果
MemFuseBench 上在三种 LLM 设置下均最优,跨源证据融合与时序推理一致提升。
💡 与研究方向关联
多源碎片记忆的融合+溯源,是 agent 长期记忆从「单一历史」走向「跨设备异构来源」的方向。
📝 原文摘要
▶ 原文摘要 Abstract
Long-term memory is essential for agents that operate across extended interactions, yet existing memory systems and benchmarks predominantly focus on single-source textual histories. In realistic settings, however, relevant information is often fragmented across applications and devices, as well as across users and time, requiring agents to integrate dispersed observations into coherent episodic memories while preserving their source provenance. To address these gaps, we introduce **MemFuseBench**, a benchmark for *multi-source memory fusion*. MemFuseBench is built with a Scene-to-Sensor pipeline that synthesizes controllable scenarios into source-tagged observations, evidence-grounded questions, and adversarial distractors. It enables systematic evaluation of temporal reasoning, cross-source evidence fusion, and robustness to noise. We further propose **MemFuse**, a structured memory system that preserves source-level evidence in event-layer atomic memory and organizes related atomic events into cluster-layer fused memory within a causal fusion graph. During retrieval, MemFuse retrieves and organizes related evidence fragments while maintaining traceability to original source events. Experiments on MemFuseBench show that MemFuse achieves the best overall performance among the evaluated memory systems under all three LLM settings and consistently improves performance on questions requiring cross-source evidence fusion.