From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting

Abstract

LLM agents are increasingly used for live forecasting, where they retrieve up-to-date information and produce estimates for unresolved future events. However, current agentic forecasting often relies on implicit narrative aggregation: agents collect evidence, discuss it in prose, and often assign a probability without an explicit update path from evidence to forecast. This limits both forecasting accuracy and auditability. We propose AuditForecast, an agentic scaffold for structured probabilisti

Categories

@misc{cao2026from,
  title = {{From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting}},
  author = {Yuanpu Cao and Yongkang Du and Yurui Chang and Lu Lin and Jinghui Chen},
  year = {2026},
  month = sep,
  eprint = {2609.05905},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.05905}
}