AgriGPT: a Large Language Model Ecosystem for Agriculture

TL;DR

AgriGPT is a specialized large language model ecosystem designed for agriculture, featuring a curated dataset, a multi-agent data engine, a retrieval-augmented reasoning framework, and a comprehensive benchmark suite, significantly advancing domain-specific AI tools.

Contribution

This work introduces AgriGPT, a novel domain-specific LLM ecosystem with a high-quality dataset, a multi-channel retrieval framework, and a new benchmark suite, addressing key challenges in applying LLMs to agriculture.

Findings

AgriGPT outperforms general-purpose LLMs in agricultural reasoning tasks.

The Tri-RAG framework enhances factual accuracy and reasoning reliability.

The ecosystem supports diverse agricultural stakeholders and promotes open research.

Abstract

Despite the rapid progress of Large Language Models (LLMs), their application in agriculture remains limited due to the lack of domain-specific models, curated datasets, and robust evaluation frameworks. To address these challenges, we propose AgriGPT, a domain-specialized LLM ecosystem for agricultural usage. At its core, we design a multi-agent scalable data engine that systematically compiles credible data sources into Agri-342K, a high-quality, standardized question-answer (QA) dataset. Trained on this dataset, AgriGPT supports a broad range of agricultural stakeholders, from practitioners to policy-makers. To enhance factual grounding, we employ Tri-RAG, a three-channel Retrieval-Augmented Generation framework combining dense retrieval, sparse retrieval, and multi-hop knowledge graph reasoning, thereby improving the LLM's reasoning reliability. For comprehensive evaluation, we introduce AgriBench-13K, a benchmark suite comprising 13 tasks with varying types and complexities. Experiments demonstrate that AgriGPT significantly outperforms general-purpose LLMs on both domain adaptation and reasoning. Beyond the model itself, AgriGPT represents a modular and extensible LLM ecosystem for agriculture, comprising structured data construction, retrieval-enhanced generation, and domain-specific evaluation. This work provides a generalizable framework for developing scientific and industry-specialized LLMs. All models, datasets, and code will be released to empower agricultural communities, especially in underserved regions, and to promote open, impactful research.