Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation
This addresses a key limitation in neural combinatorial optimization for real-world vehicle routing problems, though it is incremental as it builds on existing methods.
The paper tackles the generalization gap of neural solvers from synthetic to real-world routing problems by introducing EvoReal, which uses LLM-guided evolutionary synthesis to generate realistic instances and progressive adaptation, resulting in reduced performance gaps of 1.05% on TSPLib and 2.71% on CVRPLib benchmarks.
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.