AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models

TL;DR

This paper introduces AirTrafficGen, a novel method using large language models to automate and control the generation of complex air traffic control scenarios, enhancing diversity and realism in simulations.

Contribution

The paper presents a new graph-based encoding and prompting approach that enables LLMs to generate and refine realistic ATC scenarios, addressing manual design limitations.

Findings

LLMs can generate high-traffic, realistic ATC scenarios.

Engineered prompts allow fine-grained control over scenario features.

Models can iteratively refine scenarios based on textual feedback.

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.