A Human-in-the-Loop Autonomous Agent for Industry Time Series Forecasting
2026-08-31 • Machine Learning
Machine Learning
AI summaryⓘ
The authors introduce CastClaw, a forecasting system that helps people predict time-based data like electricity prices by combining human input with specialized models. Unlike usual models that run alone, CastClaw allows users to guide the process using natural language and checks forecasts for consistency and accuracy before finalizing them. It keeps a detailed record of all steps taken, making the whole process transparent. Tests showed it performed better than many existing methods on electricity price and load data.
time-series forecastinghuman-in-the-looplarge language modelsforecasting pipelinesmean squared errormean absolute errorelectricity price forecastingruntime execution recordNord Pool electricity marketnatural language input
Authors
Xiaoyu Tao, Mingyue Cheng, Ze Guo, Bokai Pan, Qi Liu, Shijin Wang, Enhong Chen
Abstract
Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate domain expertise, assess prediction plausibility, and communicate uncertainty. Specialized forecasting models provide strong numerical predictions but usually operate in fixed pipelines, while general-purpose large language model (LLM) agents often lack forecasting-specific checks, constraints, and stopping rules. We present CastClaw, a human-in-the-loop autonomous forecasting system built through forecasting-oriented harness engineering. CastClaw connects data, specialized models, analytical tools, user input, and a versioned execution record in one runtime. Users specify the target, horizon, constraints, and hypotheses in natural language. Starting from a supplied or model-generated forecast, CastClaw checks temporal patterns and user constraints; when evidence is missing, it retrieves context, runs an analysis or another model, or asks the user. It then keeps, revises, or escalates the result under explicit stopping conditions. The output contains the final forecast and an execution report recording inputs, evidence, actions, and revisions. In this five-dataset electricity-price setting, CastClaw reports the lowest point-estimate MSE and MAE among 16 baselines. A Nord Pool case demonstrates the inspectable workflow. CastClaw was also validated offline on provincial electricity-load data from North China covering January--June 2026.