It is challenging for autonomous control systems to perform complex tasks in the presence of latent risks. Motivated by this challenge, this paper proposes an integrated framework that involves Large Language Models (LLMs), stochastic gradient descent (SGD), and optimization-based control. In the first phrase, the proposed framework breaks down complex tasks into a sequence of smaller subtasks, whose specifications account for contextual information and latent risks. In the second phase, these subtasks and their parameters are refined through a dual process involving LLMs and SGD. LLMs are used to generate rough guesses and failure explanations, and SGD is used to fine-tune parameters. The proposed framework is tested using simulated case studies of robots and vehicles. The experiments demonstrate that the proposed framework can mediate actions based on the context and latent risks and learn complex behaviors efficiently.

翻译：在存在潜在风险的情况下，自主控制系统执行复杂任务具有挑战性。受此挑战启发，本文提出了一种集成框架，该框架融合了大语言模型（LLM）、随机梯度下降（SGD）和基于优化的控制。在第一阶段，该框架将复杂任务分解为一系列更小的子任务，其规范考虑了上下文信息和潜在风险。在第二阶段，这些子任务及其参数通过LLM和SGD的双重过程进行优化。LLM用于生成粗略估计和故障解释，而SGD则用于微调参数。通过机器人和车辆仿真案例研究，对所提框架进行了测试。实验表明，该框架能够根据上下文和潜在风险调节行为，并高效学习复杂行为。