BriefGPT.xyz
Oct, 2023
大型语言模型能成为良好的路径规划器吗?空间-时间推理的基准和研究调查
Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning
HTML
PDF
Mohamed Aghzal, Erion Plaku, Ziyu Yao
TL;DR
大型语言模型在路径规划和空间推理方面取得了显著的成功,少样本的GPT-4通过不同的提示方法在空间推理方面表现出了潜力,而微调的LLMs则在小环境或有障碍物的情况下难以推广。
Abstract
large language models
(LLMs) have achieved remarkable success across a wide spectrum of tasks; however, they still face limitations in scenarios that demand long-term planning and
spatial reasoning
. To facilitate
→