Closed-Loop LLM Co-Pilots for Digital Agriculture

用于数字农业的闭环大语言模型副驾驶系统

Abstract: This study evaluates the application of Large Language Models (LLMs) in complex biological systems, evolving from data analysis to autonomous, AI-guided experimentation. The framework is driven by data from a 49-channel phytosensor network, encompassing multispectral, electrochemical, and dielectric modalities. To enhance accessibility, the system provides real-time natural-language interpretation for both specialists and non-experts.

摘要： 本研究评估了大语言模型（LLM）在复杂生物系统中的应用，使其从单纯的数据分析演进为自主的、人工智能引导的实验。该框架由来自 49 通道植物传感器网络的数据驱动，涵盖了多光谱、电化学和介电等多种模态。为了提高易用性，该系统能为专家和非专业人士提供实时的自然语言解读。

However, its core advantage lies in the transition from human-in-the-loop analysis to autonomous control. Processing biophysical data, the LLM evaluates plant physiology and triggers hardware actuators to optimize microclimates, execute phenotyping protocols, or induce controlled stress scenarios. This closed-loop architecture establishes a direct AI-biology interface, enabling data-driven exploration of complex biosystems and ecologies.

然而，其核心优势在于从“人在回路”的分析模式向自主控制模式的转变。通过处理生物物理数据，大语言模型能够评估植物生理状态，并触发硬件执行器来优化微气候、执行表型分析方案或诱导受控的压力场景。这种闭环架构建立了一个直接的人工智能与生物学接口，实现了对复杂生物系统和生态系统的数据驱动探索。

The framework was validated across three case studies, based on a vertical farm and a single-plant setup and deciphered complex micro- and macro-fluctuations in plant physiology. Agents in a production-scale deployment executed multi-parameter optimization, balancing biomass accumulation, chlorophyll content, and energy consumption. The LLM processed biosensing telemetry to modulate full-spectrum, 450 nm, and 660 nm lighting at 2-hour intervals.

该框架通过三个案例研究进行了验证，这些研究基于垂直农场和单株植物设置，成功解析了植物生理中复杂的微观和宏观波动。在生产规模的部署中，智能体执行了多参数优化，平衡了生物量积累、叶绿素含量和能源消耗。大语言模型通过处理生物传感遥测数据，以 2 小时为间隔调节全光谱、450 纳米和 660 纳米的光照。

Compared to periodic control, the system in minimal-time mode reduced the production cycle by 35%. In the energy-optimization mode, it reduced energy consumption by 18% with only a marginal increase in cultivation time, exploiting physiological inertia via light pulses. Finally, the agents autonomously developed an unforeseen strategy of dark-induced chlorophyll accumulation, resulting in a 67.9% energy saving.

与周期性控制相比，该系统在“最短时间模式”下将生产周期缩短了 35%。在“能源优化模式”下，它通过光脉冲利用生理惯性，在仅略微增加培养时间的情况下，将能耗降低了 18%。最终，智能体自主开发出一种意想不到的“暗诱导叶绿素积累”策略，实现了 67.9% 的节能效果。

This framework transforms LLMs into autonomous co-pilots for digital agriculture, improving the cost-to-value ratio and lowering computational and expert-labor constraints.

该框架将大语言模型转化为数字农业的自主副驾驶，提高了性价比，并降低了对计算资源和专家劳动力的依赖。