AgriGPT: a Large Language Model Ecosystem for Agriculture
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916892710535168 |
|---|---|
| author | Yang, Bo Zhang, Yu Feng, Lanfei Chen, Yunkui Zhang, Jianyu Xu, Xiao Aierken, Nueraili Li, Yurui Chen, Yuxuan Yang, Guijun He, Yong Huang, Runhe Li, Shijian |
| author_facet | Yang, Bo Zhang, Yu Feng, Lanfei Chen, Yunkui Zhang, Jianyu Xu, Xiao Aierken, Nueraili Li, Yurui Chen, Yuxuan Yang, Guijun He, Yong Huang, Runhe Li, Shijian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08632 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgriGPT: a Large Language Model Ecosystem for Agriculture Yang, Bo Zhang, Yu Feng, Lanfei Chen, Yunkui Zhang, Jianyu Xu, Xiao Aierken, Nueraili Li, Yurui Chen, Yuxuan Yang, Guijun He, Yong Huang, Runhe Li, Shijian Artificial Intelligence 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. |
| title | AgriGPT: a Large Language Model Ecosystem for Agriculture |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.08632 |