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

• URL: http://arxiv.org/abs/2602.15325v1
• Date: Tue, 17 Feb 2026 03:12:57 GMT
• Title: AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
• Authors: Zhixing Zhang, Jesen Zhang, Hao Liu, Qinhan Lv, Jing Yang, Kaitong Cai, Keze Wang,
• Abstract summary: We present a Python execution environment, AgriWorld, exposing unified tools for queries over field parcels, remote-sensing time-series analytics, crop growth simulation, and task-specific predictors (e.g. yield, stress, and disease risk)<n>On top of this environment, we design a multi-turn AgroReflective agent, that iteratively writes code, observes execution results, and refines its analysis via an execute-observe-refine loop.
• Score: 17.904008870689964
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents [68.85365034738534]
  We introduce a unified framework for developing tool-augmented geospatial agents trained on satellite imagery, natural-language queries, and detailed reasoning traces.<n>The training pipeline relies on supervised fine-tuning over structured reasoning trajectories, aligning the model with verified multistep tool interactions.<n>The accompanying corpus comprises 14,538 training and 1,169 evaluation instances, with more than 100K reasoning steps in the training split and over 7K reasoning steps in the evaluation split.
  arXiv  Detail & Related papers  (2026-02-19T18:59:54Z)
• AgriGPT: a Large Language Model Ecosystem for Agriculture [16.497060004913806]
  AgriGPT is a domain-specialized Large Language Models ecosystem for agriculture usage.<n>At its core, we design a scalable data engine that compiles credible data sources into Agri-342K, a high-quality, standardized question-answer dataset.<n>We employ Tri-RAG, a three-channel Retrieval-Augmented Generation framework combining dense retrieval, sparse retrieval, and multi-hop knowledge graph reasoning.
  arXiv  Detail & Related papers  (2025-08-12T04:51:08Z)
• AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock [77.95897723270453]
  Crops, fisheries and livestock form the backbone of global food production, essential to feed the ever-growing global population.<n> Addressing these issues requires efficient, accurate, and scalable technological solutions, highlighting the importance of artificial intelligence (AI)<n>This survey presents a systematic and thorough review of more than 200 research works covering conventional machine learning approaches, advanced deep learning techniques, and recent vision-language foundation models.
  arXiv  Detail & Related papers  (2025-07-29T17:59:48Z)
• KG-FGNN: Knowledge-guided GNN Foundation Model for Fertilisation-oriented Soil GHG Flux Prediction [8.025242423352509]
  Precision soil greenhouse gas (GHG) flux prediction is essential in agricultural systems for assessing environmental impacts, developing emission mitigation strategies and promoting sustainable agriculture.<n>Due to the lack of advanced sensor and network technologies on majority of farms, there are challenges in obtaining comprehensive and diverse agricultural data.<n>This research proposes a knowledge-guided graph neural network framework that addresses the above challenges by integrating knowledge embedded in an agricultural process-based model and graph neural network techniques.
  arXiv  Detail & Related papers  (2025-06-18T21:40:24Z)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [64.86209459039313]
  ThinkGeo is an agentic benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs on 486 structured agentic tasks with 1,773 expert-verified reasoning steps.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Multimodal Agricultural Agent Architecture (MA3): A New Paradigm for Intelligent Agricultural Decision-Making [32.62816270192696]
  Modern agriculture faces dual challenges: optimizing production efficiency and achieving sustainable development.<n>To address these challenges, this study proposes an innovative textbfMultimodal textbfAgricultural textbfAgent textbfArchitecture (textbfMA3)<n>This study constructs a multimodal agricultural agent dataset encompassing five major tasks: classification, detection, Visual Question Answering (VQA), tool selection, and agent evaluation.
  arXiv  Detail & Related papers  (2025-04-07T07:32:41Z)
• AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning [30.034193330398292]
  We propose an approach to construct instruction-tuning data that harnesses vision-only data for the agriculture domain.<n>We utilize diverse agricultural datasets spanning multiple domains, curate class-specific information, and employ large language models (LLMs) to construct an expert-tuning set.<n>We expert-tuned and created AgroGPT, an efficient LMM that can hold complex agriculture-related conversations and provide useful insights.
  arXiv  Detail & Related papers  (2024-10-10T22:38:26Z)
• Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions [50.5976989558411]
  This paper investigates the faithfulness of multimodal large language model (MLLM) agents in a graphical user interface (GUI) environment.<n>A general scenario is proposed where both the user and the agent are benign, and the environment, while not malicious, contains unrelated content.<n> Experimental results reveal that even the most powerful models, whether generalist agents or specialist GUI agents, are susceptible to distractions.
  arXiv  Detail & Related papers  (2024-08-05T15:16:22Z)
• Generating Diverse Agricultural Data for Vision-Based Farming Applications [74.79409721178489]
  This model is capable of simulating distinct growth stages of plants, diverse soil conditions, and randomized field arrangements under varying lighting conditions. Our dataset includes 12,000 images with semantic labels, offering a comprehensive resource for computer vision tasks in precision agriculture.
  arXiv  Detail & Related papers  (2024-03-27T08:42:47Z)
• Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation [42.39035033967183]
  Service robots need a real-time perception system that understands their surroundings and identifies their targets in the wild. Existing methods, however, often fall short in generalizing to new crops and environmental conditions. We propose a novel approach to enhance domain generalization using knowledge distillation.
  arXiv  Detail & Related papers  (2023-04-03T14:28:29Z)
• Crop Knowledge Discovery Based on Agricultural Big Data Integration [2.597676155371155]
  Agricultural data can be generated through various sources, such as: Internet of Thing (IoT), sensors, satellites, weather stations, robots, farm equipment, agricultural laboratories, farmers, government agencies and agribusinesses. We propose an agricultural data integration method using a constellation schema which is designed to be flexible enough to incorporate other datasets and big data models.
  arXiv  Detail & Related papers  (2020-03-11T00:13:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.