Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism
This addresses over-tourism and enhances recommendation quality for users in tourism, though it is an incremental application of multi-agent systems to a domain-specific problem.
The paper tackles the problem of popularity bias and lack of diversity in tourism recommendations by proposing Collab-REC, a multi-agent LLM-based framework that balances personalization, popularity, and sustainability perspectives through negotiation, resulting in improved diversity and relevance for European city queries.
We propose Collab-REC, a multi-agent framework designed to counteract popularity bias and enhance diversity in tourism recommendations. In our setting, three LLM-based agents -- Personalization, Popularity, and Sustainability generate city suggestions from complementary perspectives. A non-LLM moderator then merges and refines these proposals via multi-round negotiation, ensuring each agent's viewpoint is incorporated while penalizing spurious or repeated responses. Experiments on European city queries show that Collab-REC improves diversity and overall relevance compared to a single-agent baseline, surfacing lesser-visited locales that often remain overlooked. This balanced, context-aware approach addresses over-tourism and better aligns with constraints provided by the user, highlighting the promise of multi-stakeholder collaboration in LLM-driven recommender systems.