Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

When AI Navigates the Fog of War

Ming Li, Xirui Li, Tianyi Zhou

Abstract

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.

When AI Navigates the Fog of War

Abstract

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.
Paper Structure (63 sections, 2 figures, 10 tables)

This paper contains 63 sections, 2 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Key Findings.
  3. Main Contributions.
  4. Broader Impacts.
  5. Background and Related Work
  6. LLMs in Geopolitical Forecasting
  7. LLMs in Multi-Actor Social and Strategic Reasoning
  8. LLM Reasoning Evaluation
  9. Data Leakage in LLM Evaluation
  10. Study Design
  11. Critical Temporal Nodes Construction
  12. Question Design
  13. Node-Specific Verifiable Questions
  14. General Exploratory Questions
  15. Interaction Protocol
  16. ...and 48 more sections

Figures (2)

  • Figure 1: Critical temporal nodes during the early stages of the 2026 Middle East conflict (top) and representative model analyses at selected nodes (bottom). Models exhibit recognizable patterns of strategic reasoning under the fog of war, and their analyses evolve as new information becomes available across the timeline.
  • Figure 2: Distribution of news articles across sources over time. The figure plots the number of news articles published by major media outlets at each temporal node.