Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Hao N. Nguyen, Hieu M. Nguyen, Son Van Nguyen, Nguyen Thi Hanh

TL;DR

LLMGreenRec is introduced, 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, which reduces unnecessary interactions and energy consumption.

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.

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

TL;DR

LLMGreenRec is introduced, 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, which reduces unnecessary interactions and energy consumption.

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.
Paper Structure (24 sections, 2 equations, 3 figures, 2 tables, 1 algorithm)

This paper contains 24 sections, 2 equations, 3 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Session-Based Recommender Systems
  4. Intent-Based Session Recommender Systems
  5. Sustainable Recommender Systems
  6. Applications of Large Language Models (LLMs)
  7. Methodology
  8. Filtering Relevant Items with Reranker Model
  9. Prompt Optimization with Multi-Agent Framework
  10. Evaluate Agent
  11. DetectError Agent
  12. InferReason Agent
  13. RefinePrompt Agent
  14. Augment Agent
  15. Select Agent
  16. ...and 9 more sections

Figures (3)

  • Figure 1: Overall workflow of LLMGreenRec
  • Figure 2: Overall pipeline of Cross-encoder reranker
  • Figure 3: Overall pipeline of the multi-agent system