{
  "id": 6082,
  "url": "https://arxiv.org/abs/2604.08987v1",
  "title": "PilotBench: A Benchmark for General Aviation Agents with Safety Constraints",
  "summary": "As Large Language Models (LLMs) advance toward embodied AI agents operating in physical environments, a fundamental question emerges: can models trained on text corpora reliably reason about complex physics while adhering to safety constraints? We address this through PilotBench, a benchmark evaluating LLMs on safety-critical flight trajectory and attitude prediction. Built from 708 real-world general aviation trajectories spanning nine operationally distinct flight phases with synchronized 34-c",
  "authors": "Yalun Wu, Haotian Liu, Zhoujun Li, Boyang Wang",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-10T05:48:38.000Z",
  "fetched_at": "2026-07-14T16:32:15.634Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6082",
  "original_url": "https://arxiv.org/abs/2604.08987v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}