ADaPT：根据需要的分解和规划与语言模型

摘要

大型语言模型（LLMs）越来越多地用于需要规划和适应环境的交互式决策任务。最近的研究以两种广泛的方式使用LLMs作为代理：迭代确定下一步动作（迭代执行者）或使用LLMs生成计划并执行子任务（计划与执行）。然而，这些方法在处理任务复杂性时存在困难，因为无法执行任何子任务可能导致任务失败。为解决这些缺点，我们引入了适应性分解和规划复杂任务（ADaPT）的方法，该方法明确计划并根据需要分解复杂子任务，即当LLM无法执行时。ADaPT递归地分解子任务以适应任务复杂性和LLM能力。我们的结果表明，ADaPT明显优于已建立的强基线，在ALFWorld中成功率高出28.3％，在WebShop中高出27％，在TextCraft中高出33％，这是我们引入的一种新颖的组合数据集。通过广泛的分析，我们阐明了多级分解的重要性，并建立了ADaPT动态调整到执行者LLM的能力以及任务复杂性的事实。

English

Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two ways: iteratively determining the next action (iterative executors) or generating plans and executing sub-tasks using LLMs (plan-and-execute). However, these methods struggle with task complexity, as the inability to execute any sub-task may lead to task failure. To address these shortcomings, we introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT), an approach that explicitly plans and decomposes complex sub-tasks as-needed, i.e., when the LLM is unable to execute them. ADaPT recursively decomposes sub-tasks to adapt to both task complexity and LLM capability. Our results demonstrate that ADaPT substantially outperforms established strong baselines, achieving success rates up to 28.3% higher in ALFWorld, 27% in WebShop, and 33% in TextCraft -- a novel compositional dataset that we introduce. Through extensive analysis, we illustrate the importance of multilevel decomposition and establish that ADaPT dynamically adjusts to the capabilities of the executor LLM as well as to task complexity.

ADaPT：根据需要的分解和规划与语言模型

ADaPT: As-Needed Decomposition and Planning with Language Models

摘要

Support