Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts

TL;DR

This paper introduces a structured LLM agent framework for post-hoc correction of agricultural yield forecasts, significantly improving prediction accuracy on proprietary and public datasets.

Contribution

It presents a novel LLM-based correction method that encodes domain knowledge to enhance existing crop yield models without requiring additional sensor data.

Findings

Agent refinement reduced MAE by 20% on strawberry datasets.

Consistent improvements observed across multiple baseline models.

Llama 3.1 8B yielded the strongest corrections among tested models.

Abstract

Accurate crop yield forecasting in commercial soft fruit production is constrained by the data available in typical commercial farm records, which lack the sensor networks, satellite imagery, and high-resolution meteorological inputs that most state-of-the-art approaches assume. We propose a structured LLM agent framework that performs post-hoc correction of existing model predictions, encoding agricultural domain knowledge across tools for phase detection, bias learning, and range validation. Evaluated on a proprietary strawberry yield dataset and a public USDA corn harvest dataset, agent refinement of XGBoost reduced MAE by 20% and MASE by 56% on strawberry, with consistent improvements across Moirai2 (MAE 24%, MASE 22%) and Random Forest (MAE 28%, MASE 66%) baselines. Using Llama 3.1 8B as the agent produced the strongest corrections across all configurations; LLaVA 13B showed inconsistent gains, highlighting sensitivity to the choice of refinement model.