English

ThinkTank-ME: A Multi-Expert Framework for Middle East Event Forecasting

Machine Learning 2026-01-27 v1 Artificial Intelligence Computation and Language Computers and Society Multiagent Systems

Abstract

Event forecasting is inherently influenced by multifaceted considerations, including international relations, regional historical dynamics, and cultural contexts. However, existing LLM-based approaches employ single-model architectures that generate predictions along a singular explicit trajectory, constraining their ability to capture diverse geopolitical nuances across complex regional contexts. To address this limitation, we introduce ThinkTank-ME, a novel Think Tank framework for Middle East event forecasting that emulates collaborative expert analysis in real-world strategic decision-making. To facilitate expert specialization and rigorous evaluation, we construct POLECAT-FOR-ME, a Middle East-focused event forecasting benchmark. Experimental results demonstrate the superiority of multi-expert collaboration in handling complex temporal geopolitical forecasting tasks. The code is available at https://github.com/LuminosityX/ThinkTank-ME.

Cite

@article{arxiv.2601.17065,
  title  = {ThinkTank-ME: A Multi-Expert Framework for Middle East Event Forecasting},
  author = {Haoxuan Li and He Chang and Yunshan Ma and Yi Bin and Yang Yang and See-Kiong Ng and Tat-Seng Chua},
  journal= {arXiv preprint arXiv:2601.17065},
  year   = {2026}
}
R2 v1 2026-07-01T09:17:52.966Z