SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
This provides a crucial benchmark for logistics and operations research to test solvers against realistic uncertainty, though it is incremental as it builds on existing routing problem frameworks.
The authors tackled the lack of realistic benchmarks for stochastic vehicle routing problems by creating SVRPBench, an open benchmark with 500+ instances simulating real-world conditions like congestion and delays, which revealed that state-of-the-art RL solvers degrade by over 20% under distributional shift.
Robust routing under uncertainty is central to real-world logistics, yet most benchmarks assume static, idealized settings. We present SVRPBench, the first open benchmark to capture high-fidelity stochastic dynamics in vehicle routing at urban scale. Spanning more than 500 instances with up to 1000 customers, it simulates realistic delivery conditions: time-dependent congestion, log-normal delays, probabilistic accidents, and empirically grounded time windows for residential and commercial clients. Our pipeline generates diverse, constraint-rich scenarios, including multi-depot and multi-vehicle setups. Benchmarking reveals that state-of-the-art RL solvers like POMO and AM degrade by over 20% under distributional shift, while classical and metaheuristic methods remain robust. To enable reproducible research, we release the dataset and evaluation suite. SVRPBench challenges the community to design solvers that generalize beyond synthetic assumptions and adapt to real-world uncertainty.