MT Travel Assistants based on Agentic AI: Survey of the State-of-the-Art and Current Challenges

Large Language Models (LLMs), Generative and Agentic AI are hot topics not just in research but in practical applications as well. For example, in the travel and tourism domain, chatbots can provide customer assistance, or LLMs can recommend detailed vacation plans. However, this domain is relatively complex, as different information sources must be combined to bundle flights, hotels, and tours or activities into a comprehensive vacation plan. Agentic AI is promising for this rather complicated task of a „travel assistant“, but solutions are not yet fully developed, in part due to problems with hallucinations of items and unreliability of recommendations, for instance.

This Master's Thesis project in Informatics (or related study programs) has two parts. The first part is to survey the start-of-the-art in Agentic AI for travel assistance. Part of the task is to classify approaches and solution options to provide an overview of the field. The goal is also to identify current issues and challenges. The resulting survey paper could be submitted to a journal such as „Information Technology & Tourism (JITT)“. In the second part, the idea is to sketch a high-level, very preliminary solution to a focused sub-problem of one of the identified challenges.

Prerequisites are high motivation and interest in this more literature-oriented topic. Please send your application (brief CV, transcript of records, and short motivation statement including ReactJS experience) to Wolfgang Wörndl (woerndl@cit.tum.de) by March 20th, 2026, with a response and decision soon after. The actual start of the thesis project is flexible.