Abstract Despite growing interest in the use of Large Language Models (LLMs) in agriculture, their integration into Extension and Advisory Services (EAS) remains underexamined. This review applies Rogers’ Diffusion of Innovation theory alongside Wüstenhagen et al.’s Social Acceptance Framework to assess current LLM applications, challenges, and contextual factors influencing their acceptance within EAS. Following a rapid review using the PRISMA framework, 12 studies were thematically analyzed first manually and then using NVivo 14. Results show that LLMs support functions such as question answering, climate analytics, and pest identification, offering innovative agronomic insights but potentially disrupting traditional EAS roles. Most LLM development is led by private firms, raising concerns about transparency, accountability, and inclusion. EAS practitioners are uniquely positioned to promote responsible LLM adoption by leveraging local knowledge and trusted relationships, though this requires targeted capacity development initiatives and inclusive strategies. This review contributes to a broader understanding of how frameworks for responsible innovation and social acceptance can inform the adoption of AI in agriculture.
Edet et al. (Mon,) studied this question.