从无状态语言模型推理到持久, 多会话自治代理的转变表明，内存是生产级代理系统部署中的主要架构瓶颈。现有的方法在很大程度上依赖于混合语义图架构,，它在摄取和检索过程中产生了大量的计算开销。这些系统通常需要大型语言模型介导的实体提取,显式图模式维护,和多查询检索管道。本文介绍了 Memanto,，这是一种用于代理人工智能的通用存储层，它挑战了知识图复杂性对于实现高保真代理内存所必需的普遍假设。 Memanto 集成了一个类型化语义记忆模式，包括十三个预定义记忆类别,、自动冲突解决机制, 和时间版本控制。这些组件由 Moorcheh的 信息论搜索引擎, 启用，这是一个无索引语义数据库，可在低于 90 毫秒的延迟内提供确定性检索，同时消除摄取延迟。通过对 LongMemEval 和 LoCoMo 评估套件进行系统基准测试，, Memanto 分别达到了 89.8% 和 87.1% 的最先进准确度分数。这些结果超越了所有经过评估的基于混合图和矢量的系统，同时仅需要单个检索查询,，不会产生任何摄取成本,，并保持较低的操作复杂性。提出了五阶段渐进消融研究，以量化每个架构组件, 的贡献，然后讨论了代理内存系统可扩展部署的影响。

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies largely depend on hybrid semantic graph architectures, which impose substantial computational overhead during both ingestion and retrieval. These systems typically require large language model mediated entity extraction, explicit graph schema maintenance, and multi query retrieval pipelines. This paper introduces Memanto, a universal memory layer for agentic artificial intelligence that challenges the prevailing assumption that knowledge graph complexity is necessary to achieve high fidelity agent memory. Memanto integrates a typed semantic memory schema comprising thirteen predefined memory categories, an automated conflict resolution mechanism, and temporal versioning. These components are enabled by Moorcheh的 Information Theoretic Search engine, a no indexing semantic database that provides deterministic retrieval within sub ninety millisecond latency while eliminating ingestion delay. Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively. These results surpass all evaluated hybrid graph and vector based systems while requiring only a single retrieval query, incurring no ingestion cost, and maintaining substantially lower operational complexity. A five stage progressive ablation study is presented to quantify the contribution of each architectural component, followed by a discussion of the implications for scalable deployment of agentic memory systems.

科目:人工智能(cs.AI)

Subjects: Artificial Intelligence (cs.AI)