3 papers
cs.DB2026
SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation
Jiacheng Ding, Xiaofei Zhang
High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constr…
cs.DB2026
TGMS: An Agent-Native Bi-Temporal Graph Management System
Xiaofei Zhang
Temporal graph questions require reliable handling of time, identifiers, and arithmetic. Large language model (LLM) agents often fail on these tasks, especially when a graph record…
cs.DB2025
ChronoConnect: Tracking Pathways Along Highly Dynamic Vertices in Temporal Graphs
Jiacheng Ding, Cong Guo, Xiaofei Zhang
With the proliferation of temporal graph data, there is a growing demand for analyzing information propagation patterns during graph evolution. Existing graph analysis systems, mos…