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

TL;DR

TRACE is a multi-agent framework using LLMs that promotes sustainable tourism by providing interactive, environmentally-conscious recommendations and explanations, encouraging user reflection without coercion.

Contribution

It introduces agentic counterfactual explanations and a modular architecture for sustainable travel recommendations, enhancing user engagement and decision quality.

Findings

User studies show effective support for sustainable decision-making.

Semantic analysis confirms alignment with environmental goals.

Implementation on Google's Agent Development Kit demonstrates practical viability.

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.