ViTSP: A Vision Language Models Guided Framework for Solving Large-Scale Traveling Salesman Problems

Researchers have developed ViTSP, a framework that uses pre-trained vision language models to solve large-scale Traveling Salesman Problems with average optimality gaps of just 0.24%. The system outperforms existing learning-based methods and reduces gaps by 3.57% to 100% compared to the best heuristic solver LKH-3 on instances with over 10,000 nodes.

• →ViTSP leverages pre-trained vision language models to visually guide solutions for large-scale TSPs without requiring dedicated model training.
• →The framework achieves 0.24% average optimality gaps on real-world TSP instances ranging from 1,000 to 88,000 nodes.
• →ViTSP outperforms existing learning-based methods and reduces gaps by 3.57% to 100% compared to LKH-3 on very large instances.
• →The approach identifies promising small-scale subproblems from visualized TSP instances and optimizes them using off-the-shelf solvers.
• →The framework demonstrates potential for integration into complex real-world logistics systems and combinatorial optimization problems.