TSR Desk · science · 21 September 2026, 07:00 UTC
Offline Multimodal Large Language Models for Decision Support in Air Operations
- What
- Offline Multimodal Large Language Models for Decision Support in Air Operations
- Who
- arxiv.org
- When
- 21 September 2026, 04:00 UTC
- Category
- Science
- Primary source
- https://arxiv.org/abs/2609.21390
- What is not known
- This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
As a first step toward evaluating this architecture, we report a pilot study with four image analysts of the Brazilian Air Force, combining (i) a doctrinal knowledge assessment based on their electronic-target identification doctrine, comparing human and proposed system performance on the same test, and (ii) a measurement of the cognitive workload involved in manually producing a reconnaissance target report (Relat\'orio de Miss\~ao de Reconhecimento - REMIR) without AI assistance. It comes from a paper posted to arXiv on 21 September 2026. Air operations rely on complex rules, established procedures, and time-critical analysis under limited connectivity and strict security constraints. In such environments, analysts must combine written doctrine with images, often without access to external computing resources. This paper studies offline large language models as decision support tools, deployed in isolated and restricted environments to give analysts access to doctrinal knowledge that remains traceable to its original sources through natural language interaction. We describe a modular retrieval-augmented architecture suitable for operation without Internet connectivity, supporting both text and image input from technical manuals. The results show a demanding manual task, especially in terms of mental demand (6.0/7) and effort (5.0/7), while the proposed system matches the human score (8/10) and completes the assessment in 7.1 minutes (compared to a human average of 26.5 minutes), establishing a baseline for future AI-assisted evaluation. Finally, we describe a future evaluation protocol to systematically compare manual and AI-assisted workflows.
Why it counts
As a first step toward evaluating this architecture, we report a pilot study with four image analysts of the Brazilian Air Force, combining (i) a doctrinal knowledge assessment based on their electronic-target identification doctrine, comparing human and proposed system performance on the same test, and (ii) a measurement of the cognitive workload involved in manually producing a reconnaissance target report (Relat\'orio de Miss\~ao de Reconhecimento - REMIR) without AI assistance.
Sources
Primary source: primary source
What is not known
This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.
No clip. The article still stands.