VoroNav is a novel semantic exploration framework designed for Zero-Shot Object Navigation (ZSON) in household robotics. It introduces the Reduced Voronoi Graph (RVG) to extract exploratory paths and planning nodes from a real-time semantic map. By integrating topological and semantic information, VoroNav generates text-based descriptions of paths and images that are interpretable by a large language model (LLM). The approach combines path and farsight descriptions to represent the environmental context, enabling LLMs to apply commonsense reasoning to select waypoints for navigation. Extensive evaluations on HM3D and HSSD datasets show that VoroNav outperforms existing benchmarks in success rate and exploration efficiency, with improvements of +2.8% Success and +3.7% SPL on HM3D, and +2.6% Success and +3.8% SPL on HSSD. Additional metrics evaluating obstacle avoidance and perceptual efficiency further validate the enhancements achieved by VoroNav in ZSON planning. The project page is available at <https://voro-nav.github.io>.VoroNav is a novel semantic exploration framework designed for Zero-Shot Object Navigation (ZSON) in household robotics. It introduces the Reduced Voronoi Graph (RVG) to extract exploratory paths and planning nodes from a real-time semantic map. By integrating topological and semantic information, VoroNav generates text-based descriptions of paths and images that are interpretable by a large language model (LLM). The approach combines path and farsight descriptions to represent the environmental context, enabling LLMs to apply commonsense reasoning to select waypoints for navigation. Extensive evaluations on HM3D and HSSD datasets show that VoroNav outperforms existing benchmarks in success rate and exploration efficiency, with improvements of +2.8% Success and +3.7% SPL on HM3D, and +2.6% Success and +3.8% SPL on HSSD. Additional metrics evaluating obstacle avoidance and perceptual efficiency further validate the enhancements achieved by VoroNav in ZSON planning. The project page is available at <https://voro-nav.github.io>.