Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism

Researchers propose Collab-REC, a multi-agent LLM framework for tourism recommendations that uses three specialized agents (Personalization, Popularity, and Sustainability) with a moderator to reduce popularity bias and increase diversity. The system successfully surfaces lesser-visited destinations and addresses over-tourism concerns through balanced, multi-perspective recommendations.

• →Collab-REC uses three LLM agents with different perspectives to generate more diverse tourism recommendations than single-agent systems.
• →The framework includes a non-LLM moderator that merges agent proposals through multi-round negotiation while penalizing repetitive responses.
• →Experiments on European city queries show the system enhances diversity and relevance compared to baseline approaches.
• →The approach specifically targets over-tourism by promoting lesser-visited destinations that are typically overlooked.
• →Multi-stakeholder collaboration in LLM-driven recommender systems shows promise for addressing bias and improving user alignment.