Papers

LLM Agent 图记忆成本:Corvic AI 与 7 款图数据库对比

Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines

Why we picked it

想给 Agent 配图记忆数据库前先看这篇,Corvic AI、Neo4j 等 8 款引擎实测,最贵的不是查询慢,是把数据喂进去。

评测团队构建了一个含 102 万节点、534 万行数据的生物医学风格属性图,并设计 20 条覆盖邻域查找、反连接、聚合、top-k 排序、时间过滤等场景的查询。

Body

测试对象为 Corvic AI 列式引擎与 LoraDB、Ladybug、DuckPGQ、Memgraph、Neo4j、HugeGraph、FalkorDB 共 7 款图数据库系统。结果显示没有系统全面最快:Ladybug 在窄邻域查询上占优,Corvic AI 在大范围扫描和连接查询上更快,DuckPGQ 仅因查询计划选择就明显偏慢。

各引擎批量摄取吞吐从 5.0k 到 430 万行/秒不等,相差 3 个数量级;

交叉点计算表明,每次数据刷新后查询量低于约 10 万次时,摄取成本主导总拥有成本。

Original · arXiv cs.AI

Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines

Graph databases are frequently positioned as categorically necessary for connected-data workloads, yet the systems dimension along which they actually differ - query planning, indexing, and data-readiness cost - is rarely isolated from vendor framing. We construct a synthetic, biomedical-shaped property graph (1.02 million nodes, 5.34 million total node and edge rows) and a twenty-query workload spanning neighborhood lookups, bounded paths, set intersections, anti-joins, grouped aggregation, top-k ranking, temporal filters, full scans, and relational joins. We benchmark Corvic AI - a purpose-built columnar query engine underlying Corvic's ontology management layer ("memories")- against seven purpose-built or graph-extension database systems (LoraDB, Ladybug, DuckPGQ, Memgraph, Neo4j, HugeGraph, and FalkorDB) at three graph scales spanning three orders of magnitude. We report query latency geomeans, bulk-ingest throughput, point-update latency, and answer correctness for each system, and we derive a simple total-cost-of-ownership model that expresses the ingest/query trade-off as a function of query volume. Our central finding is that no system in this sample is categorically fastest: a native graph engine (Ladybug) outperforms Corvic AI on narrow, bounded-neighborhood shapes, while Corvic AI is faster on shapes that scan or join a large fraction of the graph, and a system implementing graph query syntax via SQL/PGQ (DuckPGQ) is measurably slower purely due to query-plan choice. The dominant cost differential in our data is not query latency but the cost of making data queryable at all: bulk-ingest throughput varies by three orders of magnitude across engines (5.0k-4.3M rows/s), a gap that a simple crossover-point calculation shows dominates total cost for any workload with fewer than roughly 105 queries per data refresh.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Corvic AI, Neo4j, graph databases, agents.

Source attribution: curated from arXiv cs.AI (@Donald Nguyen, Gurbinder Gill, Hadi Ahmadi, Christopher J. Rossbach).