An embodied agent assisting humans is often asked to complete new tasks, and there may not be sufficient time or labeled examples to train the agent to perform these new tasks. Large Language Models (LLMs) trained on considerable knowledge across many domains can be used to predict a sequence of abstract actions for completing such tasks, although the agent may not be able to execute this sequence due to task-, agent-, or domain-specific constraints. Our framework addresses these challenges by leveraging the generic predictions provided by LLM and the prior domain knowledge encoded in a Knowledge Graph (KG), enabling an agent to quickly adapt to new tasks. The robot also solicits and uses human input as needed to refine its existing knowledge. Based on experimental evaluation in the context of cooking and cleaning tasks in simulation domains, we demonstrate that the interplay between LLM, KG, and human input leads to substantial performance gains compared with just using the LLM. Project website{\S}: https://sssshivvvv.github.io/adaptbot/

翻译：具身智能体在协助人类时经常需要完成新任务，而往往没有足够时间或标注样本来训练智能体执行这些任务。基于多领域海量知识训练的大型语言模型（LLM）可用于预测完成此类任务的抽象动作序列，但由于任务、智能体或领域特定约束，智能体可能无法执行该序列。本文提出的框架通过融合LLM提供的通用预测与知识图谱（KG）编码的领域先验知识，使智能体能够快速适应新任务。机器人还可根据需要征求并利用人类输入来精化现有知识。通过在模拟领域的烹饪与清洁任务中进行实验评估，我们证明相较于单独使用LLM，LLM、KG与人类输入三者的协同作用能带来显著的性能提升。项目网站{\S}: https://sssshivvvv.github.io/adaptbot/