LLMPC:大型语言模型预测控制
LLMPC: Large Language Model Predictive Control
AI总结:
本文从模型预测控制视角分析LLM提示技术,提出统一MPC框架,证明LLM是隐式规划成本最小化器,并在多个规划基准上优于少样本提示。
摘要:
近期,针对大型语言模型(LLMs)的提示技术的进步提升了它们的推理、规划和行动能力。本文从模型预测控制(MPC)的角度审视这些提示技术。我们表明,当使用规划提示时,LLMs充当隐式规划成本函数最小化器。我们提出了一个用于LLMs规划的统一MPC框架,并在多个规划基准上展示了相比少样本提示的改进性能。
英文摘要:
Recent advancements in prompting techniques for Large Language Models (LLMs) have improved their reasoning, planning, and action abilities. This paper examines these prompting techniques through the lens of model predictive control (MPC). We show that LLMs act as implicit planning cost function minimizers when planning prompts are used. We propose a unified MPC framework for planning with LLMs and demonstrate improved performance over few shot prompting on several planning benchmarks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。