LATIDIA · Investigación

Razonamiento LLM autoguiado para el diagnóstico de errores en problemas de enrutamiento de vehículos

arXiv: 2610.21393v1Tipo de anuncio: nuevo Resumen: Los problemas de enrutamiento de vehículos (VRP) son fundamentales para muchas aplicaciones del mundo real. Los avances recientes en los modelos de lenguaje grandes (LLM) han estimulado el progreso en la resolución de estos NP-h

La noticia

arXiv:2610.21393v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental to many real-world applications. Recent advances in large language models (LLMs) have spurred progress in solving these NP-hard problems. However, most existing approaches assume that input instances are error-free, neglecting the presence of faults commonly encountered in real-world data. In this work, we systematically investigate the capability of LLMs to detect (and correct) errors in VRP instances, and identify key limitations, particularly in handling complex instances or errors that substantially increase the LLM's reasoning burden. To overcome these challenges, we propose a self-guided reasoning framework in which LLMs autonomously generate code that provides structured insights to aid in error