The digital transformation of the tourism industry faces a dual challenge: the fragmentation of data across platforms and the lack of immersive “try-before-you-buy” experiences. While Large Language Models (LLMs) have revolutionized information synthesis, they typically lack real-time visual verification capabilities. This paper proposes a novel, multimodal AI Agent architecture that integrates advanced natural language planning with photorealistic 3D visualization. We present a system where a conversational agent, powered by Gemini 2.5 Flash, orchestrates a suite of dynamic tools to build structured travel itineraries (flights, hotels, activities) while simultaneously deploying a neural rendering engine. This engine utilizes a modular Structure-from-Motion (SfM) pipeline feeding into 3D Gaussian Splatting (3DGS) to render navigable, high-fidelity digital twins of hotel facilities directly within the chat interface. Positioned as a Technology Readiness Level 4 (TRL 4) proof of concept (PoC), this work demonstrates the technical feasibility of the multimodal integration between conversational logic and automated visual synthesis. The results demonstrate the technical feasibility of a pipeline that dynamically binds LLM inference to 3D spatial data, providing a foundation for high-fidelity, interactive travel consultancy.
Márquez-Algaba et al. (Tue,) studied this question.