{"ID":2886843,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02269","arxiv_id":"2508.02269","title":"AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models","abstract":"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.","short_abstract":"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 autom...","url_abs":"https://arxiv.org/abs/2508.02269","url_pdf":"https://arxiv.org/pdf/2508.02269v2","authors":"[\"Dewi Sid William Gould\",\"George De Ath\",\"Ben Carvell\",\"Nick Pepper\"]","published":"2025-08-04T10:21:47Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}