Recent advances in Neural Combinatorial Optimization (NCO) methods have significantly improved the capability of neural solvers to handle synthetic routing instances. Nonetheless, existing neural solvers typically struggle to generalize effectively from synthetic, uniformly-distributed training data to real-world VRP scenarios, including widely recognized benchmark instances from TSPLib and CVRPLib. To bridge this generalization gap, we present Evolutionary Realistic Instance Synthesis (EvoReal), which leverages an evolutionary module guided by large language models (LLMs) to generate synthetic instances characterized by diverse and realistic structural patterns. Specifically, the evolutionary module produces synthetic instances whose structural attributes statistically mimics those observed in authentic real-world instances. Subsequently, pre-trained NCO models are progressively refined, firstly aligning them with these structurally enriched synthetic distributions and then further adapting them through direct fine-tuning on actual benchmark instances. Extensive experimental evaluations demonstrate that EvoReal markedly improves the generalization capabilities of state-of-the-art neural solvers, yielding a notable reduced performance gap compared to the optimal solutions on the TSPLib (1.05%) and CVRPLib (2.71%) benchmarks across a broad spectrum of problem scales.

翻译：近年来，神经组合优化方法的研究进展显著提升了神经求解器处理合成路由实例的能力。然而，现有的神经求解器通常难以有效地将从合成的、均匀分布的训练数据中学到的知识，泛化到真实世界的车辆路径问题场景，包括来自TSPLib和CVRPLib的广泛认可的基准实例。为弥合这一泛化鸿沟，我们提出了进化式真实实例合成方法，该方法利用由大语言模型引导的进化模块，生成具有多样且真实结构模式的合成实例。具体而言，该进化模块生成的合成实例，其结构属性在统计意义上模拟了在真实世界实例中观察到的特征。随后，预训练的神经组合优化模型被渐进式精炼：首先使其与这些结构丰富的合成分布对齐，然后通过在真实基准实例上进行直接微调来进一步适应。大量的实验评估表明，EvoReal显著提升了最先进神经求解器的泛化能力，在TSPLib和CVRPLib基准测试中，相较于最优解的性能差距显著缩小，在广泛的问题规模范围内分别达到1.05%和2.71%。