LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce
2026-03-11 • Multiagent Systems
Multiagent SystemsInformation Retrieval
AI summaryⓘ
The authors created LLMGreenRec, a system using powerful language models to help online shoppers find eco-friendly products more easily. Unlike usual recommendation methods that focus only on quick sales, their approach understands users' green intentions better and suggests sustainable items thoughtfully. By working together in parts and refining their suggestions, this system also saves energy by cutting down unnecessary work. Tests showed it recommends eco-friendly products well and supports environmentally responsible shopping online.
Recommender SystemsLarge Language ModelsSustainable ConsumptionEco-friendly ProductsSession-based RecommendationUser Intent DetectionDigital Carbon FootprintMulti-agent SystemsPrompt EngineeringEnergy-efficient Computing
Authors
Hao N. Nguyen, Hieu M. Nguyen, Son Van Nguyen, Nguyen Thi Hanh
Abstract
Rising environmental awareness in e-commerce necessitates recommender systems that not only guide users to sustainable products but also minimize their own digital carbon footprints. Traditional session-based systems, optimized for short-term conversions, often fail to capture nuanced user intents for eco-friendly choices, perpetuating a gap between green intentions and actions. To tackle this, we introduce LLMGreenRec, a novel multi-agent framework that leverages Large Language Models (LLMs) to promote sustainable consumption. Through collaborative analysis of user interactions and iterative prompt refinement, LLMGreenRec's specialized agents deduce green-oriented user intents and prioritize eco-friendly product recommendations. Notably, this intent-driven approach also reduces unnecessary interactions and energy consumption. Extensive experiments on benchmark datasets validate LLMGreenRec's effectiveness in recommending sustainable products, demonstrating a robust solution that fosters a responsible digital economy.