A Graph-Native Bitemporal Memory Store for Conversational AI Agents
- 类型:arxiv
- 标识:2607.26520
- 链接:http://arxiv.org/abs/2607.26520v1
- 主分类:agent
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar + OpenAlex
- S2被引:0
- OpenAlex被引:0
- 影响力被引:0
- TLDR:A memory store is described: an agent-local Neo4j property graph augmented with HNSW vector indexes and a full bitemporal data model that supports point-in-time semantic retrieval without physically overwriting history.
- OpenAlex ID:W7171869971
- OpenAlex DOI:10.48550/arxiv.2607.26520
- DOI:10.48550/arxiv.2607.26520
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://doi.org/10.48550/arxiv.2607.26520
- OpenAlex更新:2026-08-25
- 待LLM分类:否
- 标题中文:面向对话式 AI Agent 的图原生双时态记忆存储
- TLDR中文:描述一个 memory store:agent 本地的 Neo4j 属性图,增强 HNSW 向量索引,并采用完整的双时态数据模型,支持时间点语义检索而无需物理覆盖历史。
- 来源文件:
- /inbox/tom/_candidates/2026-07-30-agent-rag-longcontext-candidates.json
- /inbox/tom/_candidates/2026-07-31-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]