AgroAskAI: A Multi-Agentic AI Framework for Supporting Smallholder Farmers' Enquiries Globally

2025-12-16

AI Summary

To address insufficient decision support for climate adaptation among smallholder farmers, this paper proposes a multi-agent AI framework designed for global rural communities. Methodologically, it introduces a role-based agent collaboration system featuring a novel “chain-of-responsibility coordination” architecture, integrating RAG-enhanced retrieval, real-time meteorological and agronomic API integration, multilingual LLM fine-tuning, and hallucination suppression with internal validation. The key contributions are: (1) overcoming the limitations of single-agent systems by enabling context-aware, tool-augmented, localized decision support; (2) significantly improving the actionability, factual accuracy, and geographical relevance of agronomic recommendations through dynamic collaborative reasoning and built-in governance feedback; and (3) enabling trustworthy agricultural Q&A in low-resource language settings. Experimental results demonstrate substantial performance gains over baseline models on climate-adaptation–oriented agricultural question-answering tasks.

Technology Category

• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Agricultural regions in rural areas face damage from climate-related risks, including droughts, heavy rainfall, and shifting weather patterns. Prior research calls for adaptive risk-management solutions and decision-making strategies. To this end, artificial intelligence (AI), particularly agentic AI, offers a promising path forward. Agentic AI systems consist of autonomous, specialized agents capable of solving complex, dynamic tasks. While past systems have relied on single-agent models or have used multi-agent frameworks only for static functions, there is a growing need for architectures that support dynamic collaborative reasoning and context-aware outputs. To bridge this gap, we present AgroAskAI, a multi-agent reasoning system for climate adaptation decision support in agriculture, with a focus on vulnerable rural communities. AgroAskAI features a modular, role-specialized architecture that uses a chain-of-responsibility approach to coordinate autonomous agents, integrating real-time tools and datasets. The system has built-in governance mechanisms that mitigate hallucination and enable internal feedback for coherent, locally relevant strategies. The system also supports multilingual interactions, making it accessible to non-English-speaking farmers. Experiments on common agricultural queries related to climate adaptation show that, with additional tools and prompt refinement, AgroAskAI delivers more actionable, grounded, and inclusive outputs. Our experimental results highlight the potential of agentic AI for sustainable and accountable decision support in climate adaptation for agriculture.

Problem

• Develops a multi-agent AI system for climate adaptation in agriculture
• Addresses dynamic collaborative reasoning for smallholder farmers' queries
• Provides multilingual, context-aware decision support to vulnerable rural communities

Innovation

• Multi-agent reasoning system for climate adaptation
• Modular role-specialized architecture with chain-of-responsibility
• Governance mechanisms reduce hallucination and enable feedback