A Comprehensive Survey of Retrieval-Augmented Large Language Models for Decision Making in Agriculture: Unsolved Problems and Research Opportunities

Abstract

The breakthrough in developing large language models (LLMs) over the past few years has led to their widespread implementation in various areas of industry, business, and agriculture. The aim of this article is to critically analyse and generalise the known results and research directions on approaches to the development and utilisation of LLMs, with a particular focus on their functional characteristics when integrated into decision support systems (DSSs) for agricultural monitoring. The subject of the research is approaches to the development and integration of LLMs into DSSs for agrotechnical monitoring. The main scientific and applied results of the article are as follows: the world experience of using LLMs to improve agricultural processes has been analysed; a critical analysis of the functional characteristics of LLMs has been carried out, and the areas of application of their architectures have been identified; the necessity of focusing on retrieval-augmented generation (RAG) as an approach to solving one of the main limitations of LLMs, which is the limited knowledge base of training data, has been established; the characteristics and prospects of using LLMs for DSSs in agriculture have been analysed to highlight trustworthiness, explainability and bias reduction as priority areas of research; the potential socio-economic effect from the implementation of LLMs and RAG in the agricultural sector is substantiated.