Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation
2026-07-01 • Artificial Intelligence
Artificial IntelligenceMultiagent Systems
AI summaryⓘ
The authors address challenges in farming advice systems, which either give static tips that don’t adjust to changing conditions or use AI models that can be believable but not always realistic for plants. They created Agri-SAGE, a system combining AI reasoning with a plant growth simulator to make and check farming recommendations. They tested three AI reasoning methods on past 10 years of data, all doing better than standard fixed advice, with one method producing the best crop yields and another using less computing power while still performing well. This suggests their approach can improve farming advice by balancing accuracy and resource use.
Agricultural advisory systemsLarge Language Models (LLMs)APSIM (Agricultural Production Systems Simulator)Plan-and-SolveTree of ThoughtsReflexionRetrieval-grounded reasoningBiophysical simulationPackage-of-Practice (PoP)Cross-seasonal episodic memory
Authors
Vedant Balasubramaniam, Geetha Charan, Manojkumar Patil, Rohit P Suresh, V Priyanka, Kodur Sai Vinay Sathvik, Y. Narahari
Abstract
Agricultural advisory systems face a fundamental tension: static agronomic guidelines offer consistent, evidence-based recommendations, yet remain blind to in-season variability and dynamic uncertainties. Recent advisory systems powered by LLMs are liable for a different risk of generating recommendations that are agronomically credible but physiologically unconvincing. Agri-SAGE is a closed-loop framework designed to resolve the above two limitations by integrating retrieval-grounded multi-agent LLM reasoning with APSIM-based biophysical simulation, to generate and validate agronomic advisories. To assess this framework, we evaluate three reasoning approaches, namely Plan-and-Solve, Tree of Thoughts, and Reflexion, over a 10-year retrospective analysis. All three significantly outperform static PoP (Package-of-Practice) baselines, with Tree of Thoughts achieving impressive peak yields. At the same time, Reflexion achieves comparable agronomic outcomes at substantially lower computational cost by leveraging cross-seasonal episodic memory.