LLM-Planner：基于大型语言模型的具身代理少样本接地规划
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
AI总结：
提出LLM-Planner方法，利用大型语言模型结合物理接地技术进行少样本规划，使具身代理在仅用不到0.5%训练数据时即可媲美全数据训练基线的性能。
摘要：
本研究聚焦于使用大型语言模型（LLMs）作为具身代理的规划器，使其能遵循自然语言指令在视觉感知环境中完成复杂任务。现有方法的高数据成本和低样本效率阻碍了能处理多任务并快速学习新任务的通用代理的发展。在本研究中，我们提出了一种新方法LLM-Planner，利用大型语言模型的能力为具身代理进行少样本规划。我们进一步提出了一种简单但有效的方法，通过物理接地增强LLMs，以生成和更新基于当前环境的计划。在ALFRED数据集上的实验表明，我们的方法能取得极具竞争力的少样本性能：尽管使用了不到0.5%的配对训练数据，LLM-Planner仍取得了与使用完整训练数据训练的近期基线相媲美的性能。在相同的少样本设置下，现有方法几乎无法成功完成任何任务。我们的工作为开发能快速学习多任务的通用且样本高效的具身代理打开了大门。网站：https://dki-lab.github.io/LLM-Planner
英文摘要：
This study focuses on using large language models (LLMs) as a planner for embodied agents that can follow natural language instructions to complete complex tasks in a visually-perceived environment. The high data cost and poor sample efficiency of existing methods hinders the development of versatile agents that are capable of many tasks and can learn new tasks quickly. In this work, we propose a novel method, LLM-Planner, that harnesses the power of large language models to do few-shot planning for embodied agents. We further propose a simple but effective way to enhance LLMs with physical grounding to generate and update plans that are grounded in the current environment. Experiments on the ALFRED dataset show that our method can achieve very competitive few-shot performance: Despite using less than 0.5% of paired training data, LLM-Planner achieves competitive performance with recent baselines that are trained using the full training data. Existing methods can barely complete any task successfully under the same few-shot setting. Our work opens the door for developing versatile and sample-efficient embodied agents that can quickly learn many tasks. Website: https://dki-lab.github.io/LLM-Planner
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。
