LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce

• URL: http://arxiv.org/abs/2603.11025v1
• Date: Wed, 11 Mar 2026 17:49:53 GMT
• Title: LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce
• Abstract summary: 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.<n>To tackle this, we introduce LLMGreenRec, a novel multi-agent framework that leverages Large Language Models (LLMs) to promote sustainable consumption.<n>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.
• Score: 2.350912941424321
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Bringing GRACE to Recommendation: Fine-Tuning for Sustainable and Accurate Personalization [57.58261252242669]
  Growing concern about environmental sustainability has motivated green'' recommender systems that steer users toward more eco-friendly and healthier choices.<n>Many existing green recommendation approaches require training new models from scratch, incurring substantial computational and energy costs.<n>We propose GRACE (Green Recommendation via Adaptive Conflict-rEsolution), a fine-tuning framework that integrates item-level sustainability signals into pretrained recommendation models.
  arXiv  Detail & Related papers  (2026-07-24T14:17:37Z)
• Deep Research for Recommender Systems [74.44288812684448]
  We propose a novel deep research paradigm for recommendation, which replaces conventional item lists with comprehensive, user-centric reports.<n>We instantiate this paradigm through RecPilot, a multi-agent framework comprising two core components: a user trajectory simulation agent that autonomously explores the item space, and a self-evolving report generation agent that synthesizes the findings into a coherent, interpretable report tailored to support user decisions.
  arXiv  Detail & Related papers  (2026-03-08T12:33:04Z)
• Bites of Tomorrow: Personalized Recommendations for a Healthier and Greener Plate [53.11228047172713]
  We introduce Green Recommender Aligned with Personalized Eating (GRAPE), which is designed to prioritize and recommend sustainable food options.<n>We also design two innovative Green Loss functions that cater to green indicators with either uniform or differentiated priorities.
  arXiv  Detail & Related papers  (2025-08-19T14:35:37Z)
• RecGPT Technical Report [57.84251629878726]
  We propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline.<n> RecGPT integrates large language models into key stages of user interest mining, item retrieval, and explanation generation.<n>Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders.
  arXiv  Detail & Related papers  (2025-07-30T17:55:06Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• GreenDB -- A Dataset and Benchmark for Extraction of Sustainability Information of Consumer Goods [58.31888171187044]
  We present GreenDB, a database that collects products from European online shops on a weekly basis. As proxy for the products' sustainability, it relies on sustainability labels, which are evaluated by experts. We present initial results demonstrating that ML models trained with our data can reliably predict the sustainability label of products.
  arXiv  Detail & Related papers  (2022-07-21T19:59:42Z)
• GreenDB: Toward a Product-by-Product Sustainability Database [2.9971739294416717]
  Modern retail platforms rely heavily on Machine Learning (ML) for their search and recommender systems. No open and publicly available database integrates sustainability information on a product-by-product basis. We present our proof of concept implementation of a scraping system that creates the GreenDB dataset.
  arXiv  Detail & Related papers  (2022-05-05T20:24:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.