# AgriGPT: a Large Language Model Ecosystem for Agriculture

arXiv: https://arxiv.org/abs/2508.08632 · HTML: https://mlsanity.com/paper/2508.08632/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- Retrieval-augmented generation / [Time series and agricultural RAG](https://mlsanity.com/rag/time-series-and-agricultural-rag/)

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [The role of artificial intelligence in achieving the Sustainable Development Goals](https://mlsanity.com/paper/1905.00501/) (2019)
- [A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law](https://mlsanity.com/paper/2405.01769/) (2024)
- [TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT](https://mlsanity.com/paper/2307.08674/) (2023)
- [KG-RAG: Bridging the Gap Between Knowledge and Creativity](https://mlsanity.com/paper/2405.12035/) (2024)
- [Artificial Intelligence for Social Good: A Survey](https://mlsanity.com/paper/2001.01818/) (2020)
- [AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning](https://mlsanity.com/paper/2410.08405/) (2024)
- [MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification](https://mlsanity.com/paper/2412.04494/) (2024)

## Built on by (most cited first, 11 of 11)

- [AgriGPT-VL: Agricultural Vision-Language Understanding Suite](https://mlsanity.com/paper/2510.04002/) (2025)
- [LeafNet: A Large-Scale Dataset and Comprehensive Benchmark for Foundational Vision-Language Understanding of Plant Diseases](https://mlsanity.com/paper/2602.13662/) (2026)
- [AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice](https://mlsanity.com/paper/2512.10114/) (2025)
- [AgriGPT-Omni: A Unified Speech-Vision-Text Framework for Multilingual Agricultural Intelligence](https://mlsanity.com/paper/2512.10624/) (2025)
- [From UAV Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping](https://mlsanity.com/paper/2604.09907/) (2026)
- [Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case Study](https://mlsanity.com/paper/2602.02208/) (2026)
- [AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning](https://mlsanity.com/paper/2603.14342/) (2026)
- [Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning](https://mlsanity.com/paper/2605.06121/) (2026)
- [Hallucination Behavior in Multimodal LLMs Across Agricultural Image Interpretation and Generation Tasks](https://mlsanity.com/paper/2605.27595/) (2026)
- [Fine-Tuning General-Purpose Large Language Models for Agricultural Applications:A Reproducible Framework and Evaluation Protocol Based on Qwen3-8B](https://mlsanity.com/paper/2606.28992/) (2026)
- [Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation](https://mlsanity.com/paper/2607.00454/) (2026)

## Abstract (arXiv)

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.