AgriWorld:一个用于可验证农业推理的代码执行LLM代理工具协议框架
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
AI总结：
AgriWorld通过代码执行LLM代理实现农业推理，结合执行-观察-反思循环提升农业数据处理与预测能力。
摘要：
农业基础模型越来越多地在大规模时空数据（例如多光谱遥感、土壤网格和田间管理日志）上进行训练，并在预测和监控方面取得了强劲表现。然而，这些模型缺乏基于语言的推理和交互能力，限制了它们在实际农业工作流程中的实用性。同时，大型语言模型（LLMs）擅长于解释和生成文本，但无法直接对高维、异质的农业数据集进行推理。我们通过一个农业科学的代理框架来弥合这一差距。它提供了一个Python执行环境，即AgriWorld，暴露了统一的工具，用于对田间地块进行地理空间查询、遥感时间序列分析、作物生长模拟以及任务特定的预测器（例如产量、压力和疾病风险）。在此环境中，我们设计了一个多轮LLM代理，Agro-Reflective，能够迭代编写代码、观察执行结果并通过执行-观察-反思循环来完善其分析。我们引入了AgroBench，具有可扩展的数据生成能力，用于多样化的农业问答任务，涵盖查找、预测、异常检测和反事实“如果”分析。实验结果优于纯文本和直接工具使用基线，验证了执行驱动的反思在可靠农业推理中的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
