发表机构
XDream Robotics（XDream机器人公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出受认知启发的可审计记忆架构ECHO，在LoCoMo、LongMemEval-S数据集上开展实验，对比Mem0 OSS等方法验证其性能，为长程智能体提供记忆支持。
AI 中文摘要
长程智能体需要能够识别相关经验、解决修订问题并提供可核查溯源的记忆。我们提出ECHO（Embodied Context and History Orchestration，具身上下文与历史编排），这是一种受情景编码、巩固、上下文恢复、再巩固及执行控制启发的可审计记忆架构与服务原型。该架构为功能层面的启发，而非神经层面的等效；实证分析聚焦于检索与上下文构建。在1536个LoCoMo类别1-4问题上，开发运行达到96.29%的Hit@10和73.64%的turn Recall@5；在全部500个LongMemEval-S问题上，达到97.60%的Hit@10、88.84%的turn Recall@5和88.71%的session Recall@5。五历史BEAM门表现不佳，在单独匹配的91个问答样本中，Mem0 OSS得分为64.84%，而ECHO得分为41.76%（精确McNemar检验p=0.00107），历史簇区间跨越零点。事后审计在查询扩展规则中发现了源特定短语。尽管运行时未输入标准答案字段，因此启用扩展的检索分数是描述性开发测量，而非独立确认。
英文摘要
Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Context and History Orchestration), an auditable memory architecture and service prototype inspired by episodic encoding, consolidation, contextual reinstatement, reconsolidation, and executive control. This is functional inspiration, not neural equivalence; the empirical analysis focuses on retrieval and context construction. Development runs reach 96.29% Hit@10 and 73.64% turn Recall@5 on 1,536 LoCoMo category 1-4 questions, and 97.60% Hit@10, 88.84% turn Recall@5, and 88.71% session Recall@5 on all 500 LongMemEval-S questions. A five-history BEAM gate fails, and in a separate matched 91-question QA sample Mem0 OSS scores 64.84% versus ECHO's 41.76% (exact McNemar p = 0.00107), with a history-cluster interval crossing zero. A post-hoc audit found source-specific phrases in the query-expansion rules. Although no gold answer field entered the runtime, expansion-enabled retrieval scores are therefore descriptive development measurements, not independent confirmation.
