Cyber-physical systems increasingly rely on foundational models, such as Large Language Models (LLMs) and Vision-Language Models (VLMs) to increase autonomy through enhanced perception, inference, and planning. However, these models also introduce new types of errors, such as hallucinations, over-generalizations, and context misalignments, resulting in incorrect and flawed decisions. To address this, we introduce the concept of Cognition Envelopes, designed to establish reasoning boundaries that constrain AI-generated decisions while complementing the use of meta-cognition and traditional safety envelopes. As with safety envelopes, Cognition Envelopes require practical guidelines and systematic processes for their definition, validation, and assurance. In this paper we describe an LLM/VLM-supported pipeline for dynamic clue analysis within the domain of small autonomous Uncrewed Aerial Systems deployed on Search and Rescue (SAR) missions, and a Cognition Envelope based on probabilistic reasoning and resource analysis. We evaluate the approach through assessing decisions made by our Clue Analysis Pipeline in a series of SAR missions. Finally, we identify key software engineering challenges for systematically designing, implementing, and validating Cognition Envelopes for AI-supported decisions in cyber-physical systems.

翻译：信息物理系统日益依赖基础模型，如大型语言模型（LLM）和视觉语言模型（VLM），通过增强感知、推理和规划能力来提高自主性。然而，这些模型也引入了新型错误，例如幻觉、过度泛化和上下文错位，从而导致错误和有缺陷的决策。为解决这一问题，我们提出了认知包络的概念，旨在建立推理边界，以约束人工智能生成的决策，同时补充元认知和传统安全包络的使用。与安全包络类似，认知包络需要实用的指导方针和系统化的流程来定义、验证和保证。在本文中，我们描述了一个LLM/VLM支持的动态线索分析流程，应用于部署在搜救（SAR）任务中的小型自主无人机系统领域，以及一个基于概率推理和资源分析的认知包络。我们通过评估一系列SAR任务中由线索分析流程做出的决策来验证该方法。最后，我们指出了在信息物理系统中系统化设计、实现和验证用于人工智能辅助决策的认知包络所面临的关键软件工程挑战。