Intelligent Conversational Agents for Sustainable Tourism Planning: Architecture, Implementation, and Technical Evaluation of an AI Driven Itinerary Generation System

The tourism industry faces increasing pressure to provide highly personalized experiences while maintaining environmental sustainability. In this context, recent advances in generative artificial intelligence and large language models offer new opportunities to develop systems capable of assisting travelers in planning more environmentally responsible trips. However, the effective integration of these technologies into practical tools for sustainable tourism planning remains an emerging challenge. This paper presents the design and evaluation of an intelligent conversational agent for sustainable tourism planning, developed in an experimental environment at Technology Readiness Level (TRL) 4. The system integrates large language model based conversational capabilities with external tourism information services to generate personalized travel itineraries through natural language interaction. The proposed architecture interprets user preferences and produces structured itineraries including transportation, accommodation, and activities while incorporating sustainability criteria such as carbon footprint considerations. The study demonstrates the feasibility of combining conversational AI with dynamic travel information retrieval to support sustainable tourism planning, while highlighting challenges related to heterogeneous data integration, environmental impact estimation, and real world deployment contexts. Overall, the findings provide evidence of the potential of AI based conversational agents to support hyper personalized and environmentally responsible travel planning, establishing a foundation for future research and development toward practical intelligent travel assistance systems.