AgriMAS: Multi-Agent Collaborative Framework with Retrieval-Augmented Generation for Agricultural Product Marketing Content Generation
Abstract
Generating persuasive and accurate marketing content for agricultural products is crucial for promoting regional specialties and enhancing farmer income in the digital economy era. However, existing approaches face three key limitations: (1) single-model architectures struggle to capture the multifaceted nature of marketing content requiring product knowledge, consumer insights, and creative writing skills simultaneously; (2) generic language models lack domain-specific agricultural knowledge, leading to factual errors and irrelevant content; (3) template-based methods produce repetitive outputs with limited diversity and personalization. To address these challenges, we propose AgriMAS, a multi-agent collaborative framework for agricultural product marketing content generation. Our approach introduces three key innovations: (1) a specialized multi-agent architecture in which four LLM-powered agents collaboratively handle product analysis, market research, content creation, and quality evaluation through structured message passing; (2) a retrieval-augmented generation strategy incorporating hierarchical knowledge bases with gated fusion to ground content in domain-specific agricultural information; (3) a joint optimization objective balancing generation quality, inter-agent coordination, and retrieval effectiveness. Extensive experiments on a Hunan agricultural product dataset comprising 12,847 entries demonstrate that AgriMAS achieves state-of-the-art performance with 0.423…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.