Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization

ArXi:2603.27169v1 Announce Type: new Recent research has nstrated the effectiveness of large language models (LLMs) in solving combinatorial optimization problems (COPs) by representing tasks and instances in natural language. However, purely language-based approaches struggle to accurately capture complex relational structures inherent in many COPs, rendering them less effective at addressing medium-sized or larger instances. To address these limitations, we propose AlignOPT, a novel approach that aligns LLMs with graph neural solvers to learn a generalizable neural COP heuristic.