用大模型自动生成空管训练场景，提升多样性和效率。
AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models
- 用图结构表示空域拓扑，让大模型理解并生成场景
- Gemini 2.5 Pro等模型可生成高密度、符合实际的飞行场景
- 支持细粒度控制和文本反馈修正，适合空管培训需求
人工设计空管训练场景耗时费力，限制了模拟场景的多样性。为此，我们提出端到端的AirTrafficGen方法，利用大语言模型（LLMs）自动化生成复杂空管场景。该方法采用专有的图结构表示空域拓扑（包括空域几何、航路和定位点），使模型能有效处理。通过严格基准测试，发现Gemini 2.5 Pro、OpenAI o3、GPT-oss-120b和GPT-5等先进模型能生成高流量且保持操作真实性的场景。精心设计的提示工程实现了对交互存在性、类型和位置的细粒度控制。初步结果显示，这些模型还能基于简单文本反馈进行迭代优化，修正错误场景。该方法为人工场景设计提供了可扩展替代方案，满足空管训练与验证对更多样、更大规模模拟的需求。更广泛而言，本工作展示了大模型在安全关键领域复杂规划中的潜力。
原文摘要 · Abstract (English)
The manual design of scenarios for Air Traffic Control (ATC) training is a demanding and time-consuming bottleneck that limits the diversity of simulations available to controllers. To address this, we introduce a novel, end-to-end approach, $\texttt{AirTrafficGen}$, that leverages large language models (LLMs) to automate and control the generation of complex ATC scenarios. Our method uses a purpose-built, graph-based representation to encode sector topology (including airspace geometry, routes, and fixes) into a format LLMs can process. Through rigorous benchmarking, we show that state-of-the-art models like Gemini 2.5 Pro, OpenAI o3, GPT-oss-120b and GPT-5 can generate high-traffic scenarios while maintaining operational realism. Our engineered prompting enables fine-grained control over interaction presence, type, and location. Initial findings suggest these models are also capable of iterative refinement, correcting flawed scenarios based on simple textual feedback. This approach provides a scalable alternative to manual scenario design, addressing the need for a greater volume and variety of ATC training and validation simulations. More broadly, this work showcases the potential of LLMs for complex planning in safety-critical domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。