Event prediction (EP), the accurate forecasting of future events, is vital for strategic planning and risk man-agement in both governmental and business contexts. The rapid advancement of large language models (LLMs) has positioned AI-based automated prediction methods at the forefront of academic and industrial research. However, cur-rent LLM prediction systems exhibit several shortcomings. Firstly, their information retrieval mostly searches based on the question itself, failing to gather relevant data from multi-ple perspectives as human expert teams do. Secondly, their temporal analysis is inadequate, as the collected informa-tion often includes subjective opinions or speculations and lacks the ability to reconcile contradictory information across different time points during real-time prediction. To address these issues this paper introduces MAEPS (Multi-Agent Event Prediction System), which emulates the collaborative efforts of human expert teams through 12 specialized agents. Each agent collects data from a specific professional dimension. The system automatically identifies and resolves conflict-ing information, ensuring that predictions prioritize recent and consistent facts. Experiments on EP datasets from real prediction platforms demonstrate that MAEPS significantly outperforms existing LLM prediction systems by 7% in ac-curacy, thereby validating the efficacy of simulating expert team collaboration for prediction purposes.
Jin et al. (Sun,) studied this question.