Abstract
This study evaluates the application of Large Language Models (LLMs) to complex biological systems, advancing from data analysis to autonomous, AI-guided experimentation. The framework is driven by data from a 49-channel phytosensor network that integrates multispectral, electrochemical, and dielectric modalities. To enhance accessibility, the system delivers real-time natural-language interpretation for both specialists and non-experts. However, its primary advantage lies in transitioning 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.
The framework was validated across three case studies, involving a vertical farm and a single-plant setup, and successfully deciphered complex micro- and macro-fluctuations in plant physiology. In a production-scale deployment, agents 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.
Compared to periodic control, the system in minimal-time mode reduced the production cycle by 35%. In energy-optimization mode, it reduced energy consumption by 18% with only a marginal increase in cultivation time, exploiting physiological inertia via light pulses. Notably, the agents autonomously developed an unexpected strategy of dark-induced chlorophyll accumulation, resulting in a 67.9% energy saving.
This framework transforms LLMs into autonomous co-pilots for digital agriculture, improving the cost-to-value ratio while lowering computational and expert-labor constraints. As the field moves toward more intelligent and self-sustaining agricultural systems in 2026 and beyond, such closed-loop approaches are poised to redefine the role of AI in biological research and production.
via ArXiv AI