Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zhixing Zhang, Jesen Zhang, Hao Liu, Qinhan Lv, Jing Yang, Kaitong Cai, Keze Wang

TL;DR

This work designs a multi-turn LLM agent, Agro-Reflective, that iteratively writes code, observes execution results, and refines its analysis via an execute-observe-refine loop, validating execution-driven reflection for reliable agricultural reasoning.

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.

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

TL;DR

This work designs a multi-turn LLM agent, Agro-Reflective, that iteratively writes code, observes execution results, and refines its analysis via an execute-observe-refine loop, validating execution-driven reflection for reliable agricultural reasoning.

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.
Paper Structure (35 sections, 5 equations, 2 figures, 5 tables, 1 algorithm)

This paper contains 35 sections, 5 equations, 2 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Tool-augmented LLM agents and executable reasoning.
  4. Scientific and data-centric agents for domain workflows.
  5. Benchmarks and verifiable evaluation for agentic systems.
  6. Method
  7. The World--Tools--Protocol Framework
  8. Task instance definition.
  9. Validity maximization.
  10. AgriWorld: The Executable Environment
  11. Data Model and State Space
  12. Unified Tool Interface and Artifacts
  13. Spatiotemporal Alignment and Unit Safety
  14. Canonical alignment operator.
  15. Robust Zonal Statistics.
  16. ...and 20 more sections

Figures (2)

  • Figure 1: Overview of the proposed Framework. The pipeline begins with a heterogeneous State Space $\mathcal{S}$ (e.g., geographical locations, wind fields). Data flows through functional modules such as Spatial Query, Spatio-temporal Analysis, and Crop Simulation. A critical Coordinate Alignment step transforms the raw Pre-training Sequence into a unified Aligned Sequence ($g \to kg$). Finally, the Agent validates the timeline for Temporal Errors and enforces constraints like Pattern Validity and Numerical Conservation before producing the Final Output.
  • Figure 2: Performance Scaling. Accuracy saturates logarithmically, showing efficient self-correction.