TRACE: A Conversational Framework for Sustainable Tourism Recommendation with Agentic Counterfactual Explanations

2026-04-14

AI Summary

This study addresses the limitations of conventional tourism recommendation systems, which prioritize user preferences and convenience at the expense of sustainability, often exacerbating overcrowding at popular destinations and increasing carbon emissions. To counter this, the authors propose a large language model–based multi-agent conversational framework implemented via a modular orchestrator-worker architecture using the Google Agent Development Kit. The system integrates user profiling with semantic alignment analysis and incorporates counterfactual explanations and clarifying questions during user interactions to gently encourage reflection on and adoption of greener alternatives. User studies demonstrate that the proposed approach significantly enhances support for sustainable travel decisions while preserving recommendation quality and response efficiency.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Modeling other Agents

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Traditional conversational travel recommender systems primarily optimize for user relevance and convenience, often reinforcing popular, overcrowded destinations and carbon-intensive travel choices. To address this, we present TRACE (Tourism Recommendation with Agentic Counterfactual Explanations), a multi-agent, LLM-based framework that promotes sustainable tourism through interactive nudging. TRACE uses a modular orchestrator-worker architecture where specialized agents elicit latent sustainability preferences, construct structured user personas, and generate recommendations that balance relevance with environmental impact. A key innovation lies in its use of agentic counterfactual explanations and LLM-driven clarifying questions, which together surface greener alternatives and refine understanding of intent, fostering user reflection without coercion. User studies and semantic alignment analyses demonstrate that TRACE effectively supports sustainable decision-making while preserving recommendation quality and interactive responsiveness. TRACE is implemented on Google's Agent Development Kit, with full code, Docker setup, prompts, and a publicly available demo video to ensure reproducibility. A project summary, including all resources, prompts, and demo access, is available at https://ashmibanerjee.github.io/trace-chatbot.

Problem

• sustainable tourism
• conversational recommender systems
• carbon-intensive travel
• overcrowded destinations
• user preference elicitation

Innovation

• agentic counterfactual explanations
• sustainable tourism recommendation
• multi-agent LLM framework
• interactive nudging
• modular orchestrator-worker architecture