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

TL;DR

Collab-REC is a multi-agent framework using LLMs to improve diversity and relevance in tourism recommendations by balancing perspectives like personalization, popularity, and sustainability through negotiation.

Contribution

It introduces a novel multi-agent LLM-based system that collaboratively balances multiple viewpoints to enhance recommendation diversity and relevance in tourism.

Findings

Increases diversity of recommended cities, surfacing lesser-known locales.

Improves relevance of recommendations compared to single-agent baselines.

Effectively balances multiple stakeholder perspectives in LLM-driven systems.

Abstract

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. Extensive experiments on European city queries using LLMs from different sizes and model families demonstrate that Collab-REC enhances diversity and overall relevance compared to a single-agent baseline, surfacing lesser-visited locales that are often overlooked. This balanced, context-aware approach addresses over-tourism and better aligns with user-provided constraints, highlighting the promise of multi-stakeholder collaboration in LLM-driven recommender systems. Code, data, and other artifacts are available here: https://github.com/ashmibanerjee/collab-rec, while the prompts used are included in the appendix.