构建可追溯的动态记忆系统，让AI记住并修正长期对话中的知识冲突。
WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
- 每个记忆节点都是独立世界，支持嵌套结构与内容地址化存储
- 编辑自动生成哈希审计链，实现版本追踪与矛盾共存管理
- 边类型自带行为逻辑，支持知识更新、合并与时间推理
持久化记忆是限制无状态聊天机器人向长时运行智能体演进的核心瓶颈。现有基于扁平向量库的检索增强生成（RAG）将事实切分为碎片，丢失跨会话身份，且缺乏对知识过时或矛盾的一等公民支持。尽管近期双时间知识图谱系统（Graphiti、Memento、Hydra DB）引入了带类型边和有效时间元数据，但其图结构仍为扁平：不支持递归组合，节点无内容地址不变性，边类型仅作标签。本文提出WorldDB，基于三项承诺：(i) 每个节点均为‘世界’——包含自身子图、本体范围与可组合嵌入，支持任意深度嵌套；(ii) 节点内容地址且不可变，任何编辑均触发自身及所有祖先节点哈希变更，天然生成类默克尔树审计轨迹；(iii) 边为写时程序——每种边类型自带on_insert/on_delete/on_query_rewrite处理逻辑（如覆盖关闭有效性，矛盾保留双方，same_as发起合并提案），不存在原始追加路径。在LongMemEval-s上（500问题，约11.5万词对话栈），以Claude Opus 4.7为回答器，WorldDB达成96.40%总体准确率 / 97.11%任务平均准确率，相较此前最优的Hydra DB（90.79%）提升5.61个百分点，相较Supermemory（85.20%）提升11.20个百分点，实现单会话助理完美召回，并在时间推理（96.24%）、知识更新（98.72%）和偏好合成（96.67%）上表现稳健。消融实验表明，其图层设计（统一实体解析与类型化refers_to边）独立贡献+7.0个百分点任务平均准确率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。