Forecasting Individual Dairy Cow Milk Yield via Large Language Model Orchestration

초록

Modern dairy farms continuously record individual cow milk yields, yet turning these records into on-demand forecasts requires a multi-step data-to-model pipeline that natural language alone cannot drive. We study large language model (LLM) orchestration over a verified forecasting pipeline, asking not whether it predicts yield but how faithfully it converts requests into correct tool-execution conditions. Against a deterministic Oracle pipeline, we compare a single-LLM function-calling framework and a multi-agent framework that distributes the same workflow across specialized agents. Using Gemini 2.5 Flash, both answer 1085 queries (4340 forecast points) varying in phrasing, horizon, and missingness, drawn from 13 months of commercial-farm records. On execution-matched points (those reproducing the Oracle's cow, dates, input window, and horizon), the LLM output is statistically equivalent to the Oracle (paired TOST within +/- 0.5 kg, pTOST<0.001 ), so agreement is largely fixed by the deterministic tools. This equivalence is therefore confined to execution-matched points and does not describe overall system reliability. The frameworks differ instead in fidelity: the single-LLM framework reaches only 94.31% completion (zero-filled RMSE 9.70 kg), whereas the multi-agent framework reaches 99.88% at 35% added runtime; the single-LLM losses reflect systematic date-anchoring errors and silent false-accepts, not random noise. In this case study, LLM frameworks can orchestrate verified forecasting tools, and separating responsibilities improves workflow fidelity more than accuracy.

키워드