This article experimentally evaluates whether large language models (LLMs) can generate operationally realistic ATC transmissions and outlines a concrete path and its current limits toward LLM-assisted ATC.
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.
TableManeuver is proposed, an explainable LLM-based FMR method that reformulates multivariate flight parameter time series as table-understanding inputs and combines recognition accuracy, cross-aircraft robustness, and readable step-by-step reasoning evidence, offering a practical route for applying LLMs to aviation time series analysis.
Liqiang Ren, Haipeng Wang, Xinlong Pan et al.· Entropy· 0 citations
Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that is difficult to expose with text-only red-teaming. We study automated audio-grounded red-teaming, where a text query must remain safe in isolation while the joint text-audio input induces harmful target behavior. We propose ARENA, a closed-loop framework that trains a controller on an independent 2,000case text-audio dataset. MD-Judge supplies training rewards and adaptive search feedback, while a separate, non-adaptive Llama Guard 3 evaluator alone labels final outcomes. On 520 held-out AdvBench objectives, ARENA achieves FDR/PSR of 87.9/100.0%, 71.5/96.3%, 68.1/100.0%, and 75.4/98.5% on Audio Flamingo 3, Qwen2-Audio, MiMo-Audio, and GPTAudio, respectively. Ablations show that feedback-based refinement and audio-variant search substantially improve attack discovery.
Jiaming He, Zhicong Huang, Tian Jin et al.· 0 citations
Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions.
Wentao Liu, Siyu Song, Xi Chen et al.· 0 citations
Air traffic communication (ATC) is a highly specialized domain where noisy acoustic conditions, rapid speech rates, and domain-specific terminology pose significant challenges for automatic speech recognition. We investigate the use of Speech Large Language Models (Speech LLMs) to address these challenges by combining accurate transcription with structured information extraction. We leverage publicly available ATC datasets and apply data augmentation together with metadata-enriched training, which improves multi-turn dialogue handling and reduces transcription errors. On the test set, our model achieved a word error rate of 16.70% and a role classification accuracy of 96.60%. Furthermore, we propose a system for extracting callsigns, commands, and values, enabling automated readback detection. Case studies show that the system can determine whether pilots correctly repeat critical instructions, thereby supporting safety monitoring. Taken together, these results demonstrate the potential of Speech LLMs to deliver reproducible transcription accuracy, reliable role attribution, and proactive safety monitoring in air traffic communication.
Raymond Chung· Annual International Compute...· 0 citations
Autonomous driving has progressed from rule-based subsystems and modular perception, prediction, and planning stacks toward unified data-driven architectures, and multimodal large language models (MLLMs) are increasingly proposed as the cognitive substrate of the next generation of highly automated road vehicles. This 2026 survey synthesises 39 primary sources selected from an initial corpus of 274 candidate records screened over 2020-2026, organises the field around a five-role pipeline taxonomy (perception, prediction, planning, control, and human-machine interaction), and compares six representative driving MLLMs (DriveGPT-4, LMDrive, Senna, DriveLM, GPT-4V-AD, and Cosmos-1) on accuracy, latency, and parameter footprint. A benchmark coverage matrix over LingoQA, BDD-X, DriveLM, nuScenes-QA, AutoHallu, and CODA-LM exposes evaluation gaps in prediction and planning. Model behaviour is translated into safety-assurance terms by mapping four MLLM failure-mode families to the functional-safety standard ISO 26262, the Safety of the Intended Functionality standard ISO 21448 (SOTIF), and the autonomous-systems safety-case standard UL 4600. A three-tier vehicle, edge, and cloud deployment topology is described together with the digital-twin and over-the-air update infrastructure that surrounds it. The strongest empirical finding is that Cosmos-1 delivers the best accuracy among models with sub-150 ms latency (76.6 percent mean reasoning accuracy at 480 ms), leaving verifiable safety certification as the single most important open problem for closed-loop deployment. The survey closes with a six-item research agenda spanning sub-100 ms real-time inference, out-of-distribution generalisation, multi-agent intent reasoning, verifiable safety certification, long-tail corner-case coverage, and closed-loop sim-to-real transfer. The article is intended as a reference for automotive system architects, safety engineers, regulators, and machine-learning researchers preparing the next generation of automated driving systems.
A. O. Ogar, Joshua Abah, Ali Muhammad et al.· Journal of Science Research...· 0 citations
A unified taxonomy of 8 categories covering ambiguous and unanswerable questions is addressed, a multi-agent generation pipeline with a two-stage process (NLQ generation followed by SQL grounding) and an explicit Category Conformance validation stage are addressed.
Giovanni Sullutrone, Luca Sala, Sania Aftar et al.· 0 citations