This paper studies close-loop task planning, which refers to the process of
generating a sequence of skills (a plan) to accomplish a specific goal while
adapting the plan based on real-time observations. Recently, prompting Large
Language Models (LLMs) to generate actions iteratively h
通过 Tool-Planner 框架,基于 API 函数将工具分组成一个工具包,允许大型语言模型在不同工具包之间实现计划,解决了冗余错误校正和多工具之间正确计划的挑战,实验表明该方法在不同数据集上具有很高的通过率和胜率,并优化了 GPT-4 和 Claude 3 等模型中工具学习的计划方案,展示了我们方法的潜力。