AutoRNet: Automatically Optimizing Heuristics for Robust Network Design via Large Language Models
This work addresses robust network design for applications like communication or infrastructure, but it appears incremental as it builds on existing LLM and evolutionary methods.
The authors tackled the NP-hard problem of robust network design by proposing AutoRNet, a framework that uses large language models and evolutionary algorithms to generate heuristics, which outperformed current methods by reducing manual design and dataset requirements.
Achieving robust networks is a challenging problem due to its NP-hard nature and complex solution space. Current methods, from handcrafted feature extraction to deep learning, have made progress but remain rigid, requiring manual design and large labeled datasets. To address these issues, we propose AutoRNet, a framework that integrates large language models (LLMs) with evolutionary algorithms to generate heuristics for robust network design. We design network optimization strategies to provide domain-specific prompts for LLMs, utilizing domain knowledge to generate advanced heuristics. Additionally, we introduce an adaptive fitness function to balance convergence and diversity while maintaining degree distributions. AutoRNet is evaluated on sparse and dense scale-free networks, outperforming current methods by reducing the need for manual design and large datasets.