ForecastAgentSearch: Towards a Multi-Expert Agent Search System for Geopolitical Event Forecasting
This work aims to provide an initial step toward searchable and reliable agent-based forecasting systems for geopolitical event forecasting, but it is incremental as it only outlines design challenges and possible evaluation protocols without empirical validation.
The paper proposes ForecastAgentSearch, a framework for geopolitical event forecasting that formulates the task as a multi-expert agent search problem, but it is a preliminary framework with no experimental results or concrete performance numbers.
Geopolitical event forecasting is a challenging task, as it requires understanding complex regional contexts, dynamic event signals, and uncertain future outcomes. Recent advances in large language model agents provide new opportunities for building forecasting systems that can reason with diverse sources and expert perspectives. In this paper, we present \textit{ForecastAgentSearch}, a preliminary framework that formulates geopolitical event forecasting as a multi-expert agent search problem. Given a forecasting query, the system first analyzes the task context, then searches and ranks relevant expert agents based on their regional knowledge, domain expertise, reliability, and complementarity. The selected agents provide specialized analyses, which are further coordinated to generate a final forecast with explanations and uncertainty awareness. We discuss the key design challenges of agent profiling, expert retrieval, ranking, and multi-agent coordination, and outline possible evaluation protocols for future development. This work aims to provide an initial step toward searchable and reliable agent-based forecasting systems.