用多专家协作模拟中东事件预测，提升复杂地缘政治判断力。
ThinkTank-ME: A Multi-Expert Framework for Middle East Event Forecasting
- 构建多专家框架，模拟真实战略决策中的协同分析
- 在自建基准上实现更优的中东事件预测性能
- 适合关注地缘政治、政策分析与多智能体协作的研究者
事件预测受国际关系、区域历史动态和文化背景等多重因素影响。现有基于大模型的方法多采用单模型架构，沿单一显式路径生成预测，难以捕捉复杂区域背景下多样化的地缘政治特征。为解决此问题，我们提出 ThinkTank-ME——一个面向中东事件预测的多专家协同框架，模拟现实世界战略决策中的专家协作机制。为支持专家专业化与严格评估，我们构建了 POLECAT-FOR-ME，一个聚焦中东的事件预测基准。实验表明，多专家协作在处理复杂时序地缘政治预测任务中表现更优。代码已公开于 https://github.com/LuminosityX/ThinkTank-ME。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。