发表机构
NTNU; Department of Engineering Cybernetics（挪威科技大学; 工程控制论系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究探讨大语言模型能否成为动态热环境的可解释控制器，评估五个不同规模模型在多场景下的表现。结果显示控制性能与模型复杂度有关，高复杂度模型表现更佳，整合物理模型可提升性能，还揭示了不同规模模型推理的进展，为混合控制策略提供机会。
AI 中文摘要
大语言模型（LLMs）越来越多地用于决策和推理任务，但其作为物理系统控制器的潜力仍未得到充分探索。本文研究LLMs是否能作为动态热环境的可解释控制器，考察其跟踪设定点、解释自然语言命令、推理执行器效果以及整合基于模型的先验知识的能力。在多种场景下评估了五个不同规模的LLMs，包括对加热器或风扇使用进行惩罚的设置以及模型可使用基于物理的预测工具的情况。结果表明，控制性能取决于模型复杂性：低规模和中等规模模型经常误解执行器动态或产生不一致的推理，而高复杂性模型如Qwen-3~14B和GPT-4o实现了准确的温度跟踪、稳定的执行器使用以及符合物理原理的连贯解释。整合基于物理的模型通过实现预期决策显著提高了控制平滑度和能源效率。详细的推理分类法进一步揭示了从较小模型中的因果误解到较大模型中连贯且有时间意识的推理的明显进展。研究结果表明，当LLMs具备足够能力并适当基于领域知识时，可作为可解释控制器，凸显了基于混合模型和语言驱动控制策略提供合理说明的有前景的机会。
英文摘要
Large Language Models (LLMs) are increasingly used for decision-making and reasoning tasks, yet their potential as controllers for physical systems remains largely unexplored. This work investigates whether LLMs can function as interpretable controllers for a dynamic thermal environment, examining their ability to follow setpoints, interpret natural-language commands, reason about actuator effects, and incorporate prior model-based knowledge. Five LLMs of varying scales are evaluated under multiple scenarios, including settings with penalties on heater or fan usage and cases where the models have access to a physics-based prediction tool. The results show that control performance depends on model complexity: while low- and mid-scale models frequently misinterpret actuator dynamics or generate inconsistent reasoning, high-complexity models such as Qwen-3~14B and GPT-4o achieve accurate temperature tracking, stable actuator usage, and coherent explanations aligned with physical principles. Incorporating a physics-based model significantly improves control smoothness and energy efficiency by enabling anticipatory decision-making. A detailed reasoning taxonomy further reveals a clear progression from causal misinterpretation in smaller models to cohesive and temporally aware reasoning in larger ones. The findings demonstrate that LLMs can act as interpretable controllers when sufficiently capable and appropriately grounded in domain knowledge, highlighting promising opportunities for hybrid model-based and language-driven control strategies that can provide plausible explanations.
