Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908859545681920 |
|---|---|
| author | Banerjee, Ashmi Satish, Adithi Aisyah, Fitri Nur Wörndl, Wolfgang Deldjoo, Yashar |
| author_facet | Banerjee, Ashmi Satish, Adithi Aisyah, Fitri Nur Wörndl, Wolfgang Deldjoo, Yashar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15030 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism Banerjee, Ashmi Satish, Adithi Aisyah, Fitri Nur Wörndl, Wolfgang Deldjoo, Yashar Artificial Intelligence 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. |
| title | Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15030 |