Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents

Oracle Agent Memory：面向长周期 AI 智能体的企业级记忆基座

Abstract: Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document retrieval: a memory layer must determine which interactions become durable state, how that state is scoped, how it is retrieved under latency constraints, and how it is revised or removed over time.

摘要： 智能体记忆是长周期（Long-horizon）智能体面临的一个系统性难题。在实际部署中，智能体需要跨越长时间的对话保持任务状态，在不同会话间恢复用户特定的事实和偏好，并从过往结果中积累程序性知识。这些需求远超简单的文档检索：记忆层必须能够确定哪些交互应转化为持久状态，如何界定这些状态的作用域，如何在延迟限制下进行检索，以及如何随时间推移对这些记忆进行修订或删除。

This report studies Oracle Agent Memory as a database-native memory substrate built on Oracle Database. Three themes organize the discussion: memory as a lifecycle spanning ingestion, extraction, consolidation, retrieval, summarization, and revision or removal; a layered architecture that separates an active memory core from a passive memory-store interface with explicit scope control across users, agents, and threads; and evaluation methodology in which downstream task accuracy is complemented by memory-centric measures such as evidence retrieval, recall, latency, and estimated token use.

本报告研究了作为 Oracle 数据库原生记忆基座的 Oracle Agent Memory。讨论围绕三个主题展开：一是将记忆视为涵盖摄取、提取、整合、检索、摘要以及修订或删除的生命周期；二是采用分层架构，将主动记忆核心与被动记忆存储接口分离，并对用户、智能体和线程进行明确的作用域控制；三是评估方法论，在下游任务准确率的基础上，辅以以记忆为中心的度量指标，如证据检索率、召回率、延迟和预估 Token 使用量。

The report summarizes LongMemEval results, reaching 93.8% accuracy, compares Oracle Agent Memory against flat-history baselines, using about 10.7x fewer tokens, and published or reported external baselines where available, and closes with implementation-oriented appendix material covering setup, thread lifecycle, and search semantics.

报告总结了 LongMemEval 的测试结果，准确率达到 93.8%。通过与扁平历史记录（flat-history）基准进行对比，Oracle Agent Memory 的 Token 使用量减少了约 10.7 倍。报告还对比了已发布或已知的外部基准，并在附录中提供了面向实现的材料，涵盖了设置、线程生命周期和搜索语义等内容。