AIA Forecaster: Technical Report
This work establishes a new state of the art in AI forecasting, offering practical recommendations for future research and verifiably achieving expert-level forecasting at scale.
The paper tackles the problem of judgmental forecasting using unstructured data by developing an LLM-based system called AIA Forecaster, which achieves performance equal to human superforecasters on the ForecastBench benchmark and provides additive information when combined with market consensus on a more challenging benchmark.
This technical report describes the AIA Forecaster, a Large Language Model (LLM)-based system for judgmental forecasting using unstructured data. The AIA Forecaster approach combines three core elements: agentic search over high-quality news sources, a supervisor agent that reconciles disparate forecasts for the same event, and a set of statistical calibration techniques to counter behavioral biases in large language models. On the ForecastBench benchmark (Karger et al., 2024), the AIA Forecaster achieves performance equal to human superforecasters, surpassing prior LLM baselines. In addition to reporting on ForecastBench, we also introduce a more challenging forecasting benchmark sourced from liquid prediction markets. While the AIA Forecaster underperforms market consensus on this benchmark, an ensemble combining AIA Forecaster with market consensus outperforms consensus alone, demonstrating that our forecaster provides additive information. Our work establishes a new state of the art in AI forecasting and provides practical, transferable recommendations for future research. To the best of our knowledge, this is the first work that verifiably achieves expert-level forecasting at scale.