外观
论文arXiv 2610.1347919 天前
用于安全保障的边缘案例场景生成本地 Agentic AI 框架
原文链接：A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance（arXiv 2610.13479 · 发布日期：2026-10-09）
A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance
提出在笔记本本地运行的 Agentic AI 框架，借助双 LM 循环生成并仿真评估自动系统边缘场景。
核心要点
- 边缘案例场景对自动系统训练、测试和安全保障至关重要，可暴露危险失效。
- 框架使用本地 LM、上下文知识库和 think-act-observe-update 循环生成场景。
- 第二个独立 LM 按领域准则批评场景，精炼后在仿真中运行并收集评估指标。
- 基于指标分析、聚类和文本主题分析定位功能缺口，并形成可追溯安全证据。
验证范围与局限：验证范围为生成场景的仿真运行与指标分析，摘要未说明真机或实车验证。
英文摘要 (Abstract)
Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability and robustness, ensures the system can still function safely on the boundaries of its operational design domain and learns the expected system behaviour for these edge cases. The rapid advancement in the generation and analysis capabilities of language models (LMs) has expanded their applicability and recent work has investigated LM scenario generation. However, many recent approaches rely on human-in-the-loop or rule-based strategies. This restricts the LM's ability to generate diverse and edge case scenarios; the long tail of the distribution. Our work uses local LMs in a laptop-based agentic AI framework for adaptive scenario generation. This is cheap, fully-controlled, ensures data privacy and security. It uses think, act, observe, update, and continue loops with lightweight JSON encoding to generate scenarios. We use the system requirements, system description and environment description as knowledge bases in contextual prompts for an LM to ensure scenario realism. A second, independent LM critiques each scenario using domain specific criteria so it can be refined. The refined scenarios are run in simulation and evaluation metrics collected. These metric scores are analysed and similar scenarios are created for edge cases (exploitation) or novel scenarios are generated to explore the scenario space. Post-hoc clustering using metric scores and thematic-type analysis of the rich-text scenario descriptions produced by the LM pinpoints functional gaps and their triggering conditions. This creates traceable evidence for the safety assurance case. Our work highlights the potential of a flexible and adaptive local agentic AI framework for automating edge case generation and producing traceable safety assurance evidence.
作者：Victoria J. Hodge, Colin Paterson, Rob Alexander
来源
本页事实对应的公开页面，以原文为准。