# Chat Demeter: a multi-agent system for plant disease diagnosis integrating CNN-transformer models

## TL;DR

Chat Demeter is a multi-agent system that uses AI to diagnose plant diseases with high accuracy by analyzing leaf images and providing treatment suggestions.

## Contribution

The novel contribution is a CNN-Transformer-based multi-agent system with a natural language interface for plant disease diagnosis.

## Key findings

- Chat Demeter achieves 99.50% accuracy and 99.91% AUC on the validation dataset.
- The system enables automatic identification of diseased leaves and classification of disease types.
- It offers a practical tool for crop health monitoring and disease intervention.

## Abstract

Plant diseases remain a significant challenge in global agricultural production. Achieving efficient and accurate disease detection is essential for reducing crop losses, controlling agricultural costs, and improving yields. As agriculture rapidly advances toward digitalization and intelligent transformation, the application of artificial intelligence technologies has become a key pathway to enhancing industrial competitiveness. In this study, Chat Demeter, a multi-agent system for plant disease diagnosis based on deep learning. The system captures real-time leaf images through camera devices. It employs a CNN-Transformer model to perform instance segmentation and object detection, thereby enabling automatic identification of diseased leaves and classification of disease types. To enhance interactivity and practical value, the system incorporates a natural language interface, allowing users to upload images and receive automated diagnostic results and treatment suggestions. Experimental results demonstrate that the system achieves an accuracy of 99.50% and an AUC of 99.91% on the validation dataset, highlighting its superior performance. Overall, Chat Demeter provides an effective tool for crop health monitoring and disease intervention, while offering a feasible pathway and developmental direction for integrating and optimizing future agricultural multi-agent systems.