arXiv cs.CL· Joao P. A. Dantas·· 14 小时前AI 评分27
MATE：面向空战战术决策的离线语言支持系统
Offline Language-Based Support System for Tactical Decision-Making in Air Combat Operations
AI 导读
研究团队推出离线语言支持工具 MATE，基于 RAG 从条令与战术手册中提取内容回答自然语言问题，全部组件开源、本地运行。三名巴西空军战斗机飞行员用 Llama 3.1 8B、Qwen 2.5 14B 和 Mistral NeMo 12B 对五个战术问题作答评分，五分制平均 4.00 至 4.40，Mistral NeMo 12B 得分最高，响应速度被评为完全够用，检索内容相关性是主要改进点。
正文 · 原文
Abstract:An offline language-based support tool is presented to assist pilot training and tactical decision-making in air combat operations. The system, named MATE (Mission Assistant for Training and Evaluation), applies retrieval-augmented generation (RAG) to answer natural language questions using content extracted from doctrinal and tactical manuals. Built entirely with open-source components, it performs text preprocessing, embedding generation, semantic search, and language generation locally, ensuring full offline functionality. The tool was evaluated by three Brazilian Air Force fighter pilots, who rated the answers produced with three open-weight language models (Llama 3.1 8B, Qwen 2.5 14B, and Mistral NeMo 12B) to five tactical questions derived from a publicly available air combat manual. Average ratings ranged from 4.00 to 4.40 on a five-point scale, with Mistral NeMo 12B obtaining the highest score, and the pilots rated the response time of the tool as fully adequate compared to manual search. The relevance of the retrieved content was identified as the main point for improvement. Potential applications are discussed in onboard mission systems, flight simulators, and training environments.
| Comments: | Accepted at the LatinX in AI Workshop @ NeurIPS 2025. 7 pages, 2 figures, 2 tables |
| Subjects: | Computation and Language (cs.CL); Human-Computer Interaction (cs.HC) |
| ACM classes: | I.2.7; H.3.3 |
| Cite as: | arXiv:2610.35635 [cs.CL] |
| (or arXiv:2610.35635v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35635 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joao Dantas [view email]
[v1]
Mon, 26 Oct 2026 15:46:03 UTC (34 KB)
来源：arXiv cs.CL · arxiv.org