We introduce Strategic Doctrine Language Models (sdLM), a learning-system framework for multi-document strategic reasoning with doctrinal consistency constraints and calibrated uncertainty. The approach combines multi-document attention, temporal encoding, and a doctrine-consistency layer to improve long-horizon forecasting and plan plausibility while reducing severe doctrinal violations. We evaluate sdLM using (i) expert-panel scoring of strategic scenarios (N=47), (ii) doctrine consistency on 336 doctrine publications (12,847 statements), and (iii) geopolitical forecasting on 127 historical counterfactuals (1945-2020) across 12-60 month horizons. Across these benchmarks, sdLM achieves higher strategic quality and better calibration than strong general-purpose LLM baselines, and remains competitive with human experts on long-horizon judgments. We further report ablations, scaling trends, and deployment-oriented performance/latency characteristics to clarify which components drive improvements and how they translate to operational settings.

翻译：本文提出战略学说语言模型（sdLM），这是一个具备学说一致性约束与校准不确定性的多文档战略推理学习系统框架。该方法融合了多文档注意力机制、时序编码以及学说一致性层，旨在提升长期预测与计划合理性，同时减少严重的学说违背。我们通过以下三个方面评估sdLM：（一）由专家小组对战略情景（N=47）进行评分；（二）在336份学说出版物（12,847条陈述）上的学说一致性检验；（三）对127个历史反事实事件（1945–2020年）在12至60个月预测期内的地缘政治预测。在上述基准测试中，sdLM相比强大的通用大语言模型基线，展现出更高的战略质量与更好的校准效果，并在长期判断上与人类专家保持竞争力。我们进一步报告了消融实验、扩展趋势以及面向部署的性能/延迟特性，以阐明哪些组件驱动了性能提升，以及它们如何转化为实际应用场景。