Air Traffic Control Using Large Language Models: Prompt Engineering, Architecture, and Evaluation

• URL: http://arxiv.org/abs/2608.19299v2
• Date: Wed, 26 Aug 2026 15:31:53 GMT
• Title: Air Traffic Control Using Large Language Models: Prompt Engineering, Architecture, and Evaluation
• Abstract summary: We experimentally evaluate whether large language models (LLMs) can generate operationally realistic air traffic control transmissions.<n>A general-aviation flight flying over the San Francisco "Bay Tour" route is hand-transcribed and used as ground truth (P0).<n>Across nine open- and closed-source LLMs we vary the prompt, the presence of a worked transcript from a different experimental flight as an in-context example, and whether the model conditions on its own prior replies or on injected ground-truth history.
• Score: 36.21888090037439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Air traffic control (ATC) communication is a safety-critical dialogue that remains largely human-driven even as other parts of air traffic management have been semi-automated. In this article, we experimentally evaluate whether large language models (LLMs) can generate operationally realistic ATC transmissions. An experimental general-aviation flight flying over the San Francisco "Bay Tour" route is hand-transcribed and used as ground truth (P0). Through a pilot-in-the-loop process we design five prompt structures (P1-P5) of increasing constraint and embed them in a stateful multi-turn pipeline, where the model plays ATC to a fixed pilot transcript while conditioning on the accumulating dialogue history. Across nine open- and closed-source LLMs we vary the prompt, the presence of a worked transcript from a different experimental flight as an in-context example, and whether the model conditions on its own prior replies or on injected ground-truth history. Turns are scored with lexical, structural, and semantic similarity metrics and by an LLM-as-judge (GPT-5.5) validated against human expert annotation. Supplying a worked example improves similarity, but tightening the prompt does not: the lightest prompts perform best and the most heavily scripted one collapses as its own errors accumulate through the dialogue, which injecting correct history repairs. These results outline a concrete path and its current limits toward LLM-assisted ATC.

Related papers

• Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approach [14.220005377497259]
  We propose FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis.<n>We first perform feature engineering to address modal inconsistency, combining statistical descriptors with physically meaningful flight indicators.<n>This representation is processed by a Semantic Discretization module, which converts abstract numerical patterns into qualitative descriptions.
  arXiv  Detail & Related papers  (2026-08-18T17:11:40Z)
• SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring [8.082279149607116]
  Air Traffic Control (ATC) voice instructions are a primary safeguard against miscommunication in air transportation.<n>Readback anomalies remain implicated in approximately 80% of aviation incidents.<n>Traditional rule-based and machine learning approaches struggle to generalize across the highly variable and evolving phraseology of ATC communications.<n>We propose a novel lightweight-training LLM framework that advances both the efficiency and accuracy of machine-based ATC readback monitoring.
  arXiv  Detail & Related papers  (2026-05-28T07:56:24Z)
• SOMA: Efficient Multi-turn LLM Serving via Small Language Model [64.50946708641608]
  Large Language Models (LLMs) are increasingly deployed in multi-turn dialogue settings.<n>We propose a framework that exploits the early turns of a session to estimate a local response manifold.<n>We distill the mined cases into localized LoRA fine-tuning so the surrogate runs without prompts at inference.
  arXiv  Detail & Related papers  (2026-05-11T23:07:33Z)
• AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models [0.004807514276707785]
  We introduce a novel, end-to-end approach to generate complex Air Traffic Control scenarios.<n>Our method uses a purpose-built, graph-based representation to encode sector topology.<n>We show that state-of-the-art models like Gemini 2.5 Pro can generate high-traffic scenarios while maintaining operational realism.
  arXiv  Detail & Related papers  (2025-08-04T10:21:47Z)
• LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation [102.1527101235251]
  LangTraj is a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios.<n>By conditioning on natural language inputs, LangTraj provides flexible and intuitive control over interactive behaviors.<n>LangTraj demonstrates strong performance in realism, language controllability, and language-conditioned safety-critical simulation.
  arXiv  Detail & Related papers  (2025-04-15T17:14:06Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.931194824519935]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving [69.82743399946371]
  DriveMLM is a framework that can perform close-loop autonomous driving in realistic simulators. We employ a multi-modal LLM (MLLM) to model the behavior planning module of a module AD system. This model can plug-and-play in existing AD systems such as Apollo for close-loop driving.
  arXiv  Detail & Related papers  (2023-12-14T18:59:05Z)
• A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers [0.797970449705065]
  We propose a novel virtual simulation-pilot engine for speeding up air traffic controller (ATCo) training. The engine receives spoken communications from ATCo trainees, and it performs automatic speech recognition and understanding. To the best of our knowledge, this is the first work fully based on open-source ATC resources and AI tools.
  arXiv  Detail & Related papers  (2023-04-16T17:45:21Z)
• Inferring Traffic Models in Terminal Airspace from Flight Tracks and Procedures [39.89295870460643]
  We propose a simple probabilistic model that can learn variability from procedural data and flight tracks collected from radar surveillance data.<n>We generate synthetic trajectories by sampling a series of deviations from the Gaussian mixture model and reconstructing the aircraft trajectory.<n>We demonstrate the proposed models on the arrival tracks and procedures of the John F. Kennedy International Airport.
  arXiv  Detail & Related papers  (2023-03-17T13:58:06Z)
• Speech and Natural Language Processing Technologies for Pseudo-Pilot Simulator [0.5480546613836199]
  This paper describes a simple yet efficient repetition-based modular system for speeding up air-traffic controllers (ATCos) training. E.g., a human pilot is still required in EURO's ESCAPE lite simulator (see https://www.eurocontrol.int/simulator/escape) during ATCo training. This need can be substituted by an automatic system that could act as a pilot.
  arXiv  Detail & Related papers  (2022-12-14T11:34:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.