Logo image
Multi-agent collaboration strategies for tourism demand forecasting
Journal article   Peer reviewed

Multi-agent collaboration strategies for tourism demand forecasting

Doris Chenguang Wu, Peiying Zhang, Ji Wu, Gang Li and Mingming Hu
Tourism management, Vol.118, 105479
02/2027

Abstract

Chain collaboration Multi-agent collaboration Multi-role Parallel collaboration Tourism forecasting
With the advancement of LLM-based agents, multi-agent collaboration has attracted growing interdisciplinary attention. However, its effectiveness in business planning and decision-making remains underexplored. Therefore, this study proposes different multi-agent collaboration strategies and examines their effectiveness in such business tasks as tourism demand forecasting. The results based on Hong Kong daily inbound tourist data show that there is variability in agent forecasting performance guided by different strategies. The parallel collaboration significantly outperforms both non-collaboration and chain collaboration. Meanwhile, the performance of chain collaboration depends on agent number, independent forecasting ability, and agent order. Furthermore, heterogeneous multi-LLM collaboration consistently exceeds homogeneous multi-role collaboration. This study offers valuable insights and evidence for the design of multi-agent collaboration strategies in business scenarios.

Metrics

1 Record Views

Details

Logo image

Usage Policy