用预测控制框架提升大模型的规划能力
LLMPC: Large Language Model Predictive Control
- 将大模型规划视为隐式成本函数优化
- 在多个基准上优于少样本提示方法
- 为大模型规划提供统一理论框架
大语言模型（LLM）的提示技术进步提升了其推理、规划和行动能力。本文从模型预测控制（MPC）视角分析这些提示技术，发现使用规划提示时，LLM实质上在最小化隐式规划成本函数。我们提出一个统一的基于LLM的规划MPC框架，并在多个规划基准测试中展示了相比少样本提示的性能提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。