DynGraphAgentBench: A Benchmark for Agentic Lifecycle Control in Dynamic Graph Anomaly Detection
Dynamic graph anomaly detection requires repeated decisions as graph structure and class prevalence drift, yet detector benchmarks usually score a fixed pipeline after current labels are known. We introduce DynGraphAgentBench, an executable benchmark for agentic lifecycle control under delayed feedback. It comprises se...
Yu-Wei Han, Ling-Wei Wei, Wooseong Yang et al.
· 0 citations