WorldDB：一种带有本体感知写时 reconciliation 的向量图-世界内存引擎
WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
AI总结：
WorldDB通过引入世界概念、内容地址化和写时程序化边，解决了传统内存系统在跨会话身份丢失和冲突处理上的不足，实现了更高的准确率和鲁棒性。
摘要：
持久内存是将无状态聊天机器人与长运行的代理系统区分开来的瓶颈。检索增强生成（RAG）在扁平向量存储上将事实分割成块，丢失跨会话身份，并没有第一类的超时或矛盾概念。最近的双时间知识图谱系统（Graphiti、Memento、Hydra DB）添加了类型边和有效时间元数据，但图本身仍保持扁平：没有递归组成，没有节点的内容地址化不变量，且边类型仅携带标签之外的行为。我们提出了WorldDB，一种基于三个承诺的内存引擎：（i）每个节点都是一个世界——一个包含自身子图、本体范围和组合嵌入的容器，递归到任意深度；（ii）节点是内容地址化的且不可变的，因此任何编辑都会在节点和所有祖先生成新的哈希，从而免费提供Merkle风格的审计轨迹；（iii）边是写时程序——每种边类型携带on_insert/on_delete/on_query_rewrite处理程序（超时关闭有效性，矛盾保持双方，same_as阶段合并提案），因此不存在原始追加路径。在LongMemEval-s（500个问题，约115,000个token的对话堆栈）上，WorldDB与Claude Opus 4.7作为回答者实现了96.40%的总体准确率/97.11%的任务平均准确率，比之前报告的Hydra DB的最先进水平（90.79%）提高了5.61个百分点，比Supermemory（85.20%）提高了11.20个百分点，具有完美的单会话助理召回率和在时间推理（96.24%）、知识更新（98.72%）和偏好合成（96.67%）上的稳健性能。消融实验显示，引擎的图层——统一的实体解析和类型refers_to边——独立于底层回答者贡献了+7.0个百分点的任务平均准确率。
英文摘要：
Persistent memory is the bottleneck separating stateless chatbots from long-running agentic systems. Retrieval-augmented generation (RAG) over flat vector stores fragments facts into chunks, loses cross-session identity, and has no first-class notion of supersession or contradiction. Recent bitemporal knowledge-graph systems (Graphiti, Memento, Hydra DB) add typed edges and valid-time metadata, but the graph itself remains flat: no recursive composition, no content-addressed invariants on nodes, and edge types carry no behavior beyond a label. We present WorldDB, a memory engine built on three commitments: (i) every node is a world -- a container with its own interior subgraph, ontology scope, and composed embedding, recursive to arbitrary depth; (ii) nodes are content-addressed and immutable, so any edit produces a new hash at the node and every ancestor, giving a Merkle-style audit trail for free; (iii) edges are write-time programs -- each edge type ships on_insert/on_delete/on_query_rewrite handlers (supersession closes validity, contradicts preserves both sides, same_as stages a merge proposal), so no raw append path exists. On LongMemEval-s (500 questions, ~115k-token conversational stacks), WorldDB with Claude Opus 4.7 as answerer achieves 96.40% overall / 97.11% task-averaged accuracy, a +5.61pp improvement over the previously reported Hydra DB state-of-the-art (90.79%) and +11.20pp over Supermemory (85.20%), with perfect single-session-assistant recall and robust performance on temporal reasoning (96.24%), knowledge update (98.72%), and preference synthesis (96.67%). Ablations show that the engine's graph layer -- resolver-unified entities and typed refers_to edges -- contributes +7.0pp task-averaged independently of the underlying answerer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
