AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

TL;DR

This paper introduces AgriWorld, a framework combining language models with a Python environment for agricultural data analysis, enabling reasoning, simulation, and interactive decision-making in agronomy.

Contribution

It presents a novel agentic framework that integrates LLMs with geospatial and agricultural tools for improved reasoning and decision support.

Findings

Outperforms text-only and direct tool-use baselines.

Enables iterative code writing and refinement for complex tasks.

Supports diverse agricultural QA and counterfactual analysis.

Abstract

Foundation models for agriculture are increasingly trained on massive spatiotemporal data (e.g., multi-spectral remote sensing, soil grids, and field-level management logs) and achieve strong performance on forecasting and monitoring. However, these models lack language-based reasoning and interactive capabilities, limiting their usefulness in real-world agronomic workflows. Meanwhile, large language models (LLMs) excel at interpreting and generating text, but cannot directly reason over high-dimensional, heterogeneous agricultural datasets. We bridge this gap with an agentic framework for agricultural science. It provides a Python execution environment, AgriWorld, exposing unified tools for geospatial queries over field parcels, remote-sensing time-series analytics, crop growth simulation, and task-specific predictors (e.g., yield, stress, and disease risk). On top of this environment, we design a multi-turn LLM agent, Agro-Reflective, that iteratively writes code, observes execution results, and refines its analysis via an execute-observe-refine loop. We introduce AgroBench, with scalable data generation for diverse agricultural QA spanning lookups, forecasting, anomaly detection, and counterfactual "what-if" analysis. Experiments outperform text-only and direct tool-use baselines, validating execution-driven reflection for reliable agricultural reasoning.