Memanto：具備資訊理論檢索機制的類型化語義記憶框架——面向長週期智能體的設計（註：Memanto作為專有名詞保留原文，通過破折號補充說明其技術特性與應用場景，既保持術語一致性又實現學術表述的準確性。"Typed Semantic Memory"譯為「類型化語義記憶」符合計算機科學領域類型系統的術語規範，"Information-Theoretic Retrieval"採用「資訊理論檢索」這一資訊論標準譯法，後置定語通過「面向...設計」的句式實現自然語序調整。）

摘要

從無狀態語言模型推論到持久性多會話自主代理的轉變，揭示了記憶體已成為生產級代理系統部署中的主要架構瓶頸。現有方法主要依賴混合式語義圖架構，這種架構在資料攝取和檢索階段都會產生大量計算開銷。這些系統通常需要大型語言模型介導的實體提取、顯式圖模式維護以及多查詢檢索管道。本文提出Memanto——一種面向代理人工智慧的通用記憶體層，該設計對「必須通過複雜知識圖譜才能實現高保真代理記憶」的主流假設提出了挑戰。Memanto整合了包含十三個預定義記憶類別的類型化語義記憶模式、自動衝突解決機制和時態版本控制功能。這些組件由Moorcheh資訊理論搜索引擎驅動，這是一種無索引語義數據庫，可在90毫秒延遲內實現確定性檢索，同時消除攝取延遲。通過在LongMemEval和LoCoMo評估套件上進行系統化基準測試，Memanto分別達到了89.8%和87.1%的尖端準確率。這些結果超越了所有經過評估的混合圖譜與向量系統，且僅需單次檢索查詢、無需攝取成本，並保持顯著更低的運維複雜度。本文通過五階段漸進式消融研究量化各架構組件的貢獻度，最後探討了對代理記憶系統可擴展部署的啟示。

English

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's 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.

Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents

摘要

Support