MiLoop: Selective Memory Propagation for Neural Combinatorial Optimization

Excerpt

arXiv:2610.01685v1 Announce Type: new Abstract: Constructive neural combinatorial optimization (NCO) has emerged as a promising paradigm that learns to construct solutions to combinatorial optimization problems (COPs) step by step, which reduces reliance on handcrafted rules and enables fast inference. While many methods with dynamic embeddings generalize well, they typically rebuild subproblem representations from scratch at each step using deep attention stacks. Many high-performing methods in