DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents

DynaSchedBench is a new diagnostic framework for the Dynamic Flexible Job Shop Scheduling Problem (DFJSP), addressing limitations in neural combinatorial optimization. It uses a Sequential Event-Space Calibrator (SESC) and Schedule Stress Index (SSI) to rigorously control instance generation and stratify difficulty. This method proves more efficient than evolutionary baselines, enabling rigorous testing of LLM-based scheduling agents.