Saved in:
Bibliographic Details
Main Authors: Zhang, Zhixing, Zhang, Jesen, Liu, Hao, Lv, Qinhan, Yang, Jing, Cai, Kaitong, Wang, Keze
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15325
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914334169366528
author Zhang, Zhixing
Zhang, Jesen
Liu, Hao
Lv, Qinhan
Yang, Jing
Cai, Kaitong
Wang, Keze
author_facet Zhang, Zhixing
Zhang, Jesen
Liu, Hao
Lv, Qinhan
Yang, Jing
Cai, Kaitong
Wang, Keze
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15325
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
Zhang, Zhixing
Zhang, Jesen
Liu, Hao
Lv, Qinhan
Yang, Jing
Cai, Kaitong
Wang, Keze
Artificial Intelligence
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.
title AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2602.15325