arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.16642cs.AIcs.CLcs.CY
收藏

当AI穿越战争的迷雾

When AI Navigates the Fog of War

Mohamed bin Zayed University of Artificial Intelligence(莫扎德·本·扎耶德人工智能大学);University of Maryland, College Park(马里兰大学学院市分校)

Ming Li, Xirui Li, Tianyi Zhou

AI总结:

本文研究AI在战争初期预测能力,通过2026年中东冲突案例,测试模型在无训练数据泄露情况下分析危机的能力,揭示模型在不同领域中的策略现实性和叙事演变。

摘要:

AI能否在战争轨迹历史明显之前进行推理?分析此能力具有挑战性,因为回顾性地缘政治预测严重受训练数据泄露影响。本文通过2026年中东冲突早期阶段的时序案例研究,该冲突发生在当前前沿模型训练截止后。我们构建了11个关键时间节点,42个节点特定可验证问题和5个通用探索性问题,要求模型仅基于每个时刻公开可用的信息进行推理。此设计显著减轻了训练数据泄露问题,创造了一个适合研究模型在战争迷雾中分析发展中的危机的环境,并提供了我们所知的第一个基于时间的LLM推理分析。我们的分析揭示了三个主要发现:第一,当前最先进的大语言模型往往表现出显著的战略现实性,推理超越表面言辞,深入结构性激励。第二,这种能力在不同领域不均:模型在经济和后勤结构设置中更可靠,而在政治模糊的多主体环境中更不可靠。第三,模型叙事随时间演变,从早期对快速遏制的期望转向更系统性的区域扎根和消耗性缓和。由于冲突在写作时仍持续,这项工作可以作为模型推理在发展中的地缘政治危机的档案快照,使未来研究避免回顾性分析的偏见。

英文摘要:

Can AI reason about a war before its trajectory becomes historically obvious? Analyzing this capability is difficult because retrospective geopolitical prediction is heavily confounded by training-data leakage. We address this challenge through a temporally grounded case study of the early stages of the 2026 Middle East conflict, which unfolded after the training cutoff of current frontier models. We construct 11 critical temporal nodes, 42 node-specific verifiable questions, and 5 general exploratory questions, requiring models to reason only from information that would have been publicly available at each moment. This design substantially mitigates training-data leakage concerns, creating a setting well-suited for studying how models analyze an unfolding crisis under the fog of war, and provides, to our knowledge, the first temporally grounded analysis of LLM reasoning in an ongoing geopolitical conflict. Our analysis reveals three main findings. First, current state-of-the-art large language models often display a striking degree of strategic realism, reasoning beyond surface rhetoric toward deeper structural incentives. Second, this capability is uneven across domains: models are more reliable in economically and logistically structured settings than in politically ambiguous multi-actor environments. Finally, model narratives evolve over time, shifting from early expectations of rapid containment toward more systemic accounts of regional entrenchment and attritional de-escalation. Since the conflict remains ongoing at the time of writing, this work can serve as an archival snapshot of model reasoning during an unfolding geopolitical crisis, enabling future studies without the hindsight bias of retrospective analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑