一句话：提出 LLM 驱动的自主系统验证框架，统一场景生成、仿真执行与遥测分析，并由失败反事实生成新测试形成闭环。
自主赛博物理系统（如无人机）的验证实践在场景设计、仿真执行与遥测分析之间彼此割裂，导致需求、测试与证据之间缺乏可追溯性，复现性差、调试与迭代缓慢，难以在复杂多变的环境条件下进行系统化保障。本文提出 AutonomyLens，一个由 LLM 驱动的框架，将场景规约、仿真执行与遥测分析整合为统一的验证工作流：开发者可将高层验证意图翻译为可执行、随时间演化的场景，自动运行仿真，并对系统行为进行上下文感知分析。框架包含四部分：(i) 任务级场景的结构化表示，(ii) 自动化执行流水线，(iii) 将遥测与场景上下文对齐以产出可操作洞见的分析机制，(iv) 反事实场景生成，从观测到的失败中精化并合成新测试用例以闭合循环。论文描述其早期设计，讨论构建集成验证工作流的关键挑战，并展望其对可追溯性、复现性与可扩展性的改善。
Software engineering practices for validating autonomous cyber-physical systems (e.g., Uncrewed Aerial Vehicles) remain fragmented across scenario design, simulation execution, and telemetry analysis, limiting traceability between requirements, tests, and evidence. This fragmentation reduces reproducibility, slows debugging and iteration, and hinders systematic assurance under complex and evolving environmental conditions. We present AutonomyLens, an LLM-driven framework that integrates scenario specification, simulation execution, and telemetry analysis into a unified validation workflow. AutonomyLens enables developers to translate high-level validation intent into executable, temporally evolving scenarios, automatically run simulations, and perform context-aware analysis of resulting system behavior. The framework introduces (i) a structured representation for missionlevel scenarios, (ii) an automated execution pipeline, (iii) analysis mechanisms that align telemetry with scenario context to produce actionable insights, and (iv) counterfactual scenario generation that closes the loop by refining and synthesizing new test cases from observed failures. We describe the early-stage design of Autono-myLens, discuss key challenges in building integrated validation workflows for autonomous systems, and outline how such an approach can improve traceability, reproducibility, and scalability in autonomy validation.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2604-11672,
title = {AutonomyLens: A Self-Evolving Simulation-Based Testing Loop for Autonomous Systems},
author = {Ankit Agrawal and Jithin Garapati and Bohan Zhang},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805539}
}