ADaPT：根據需要進行分解和規劃與語言模型

摘要

大型語言模型（LLMs）越來越多地用於需要規劃和適應環境的互動決策任務。最近的研究以兩種廣泛的方式使用LLMs作為代理：迭代確定下一步行動（迭代執行者）或使用LLMs生成計劃並執行子任務（計劃和執行）。然而，這些方法在處理任務複雜性時存在困難，因為無法執行任何子任務可能導致任務失敗。為了解決這些缺點，我們引入了針對複雜任務的按需分解和規劃（ADaPT）方法，該方法明確地規劃和分解複雜子任務，即在LLM無法執行時進行。ADaPT遞歸地分解子任務以適應任務複雜性和LLM能力。我們的結果表明，ADaPT在ALFWorld中的成功率高出28.3％，在WebShop中高出27％，在TextCraft中高出33％，這是我們介紹的一個新的組合數據集。通過廣泛的分析，我們說明了多級分解的重要性，並確立了ADaPT根據執行者LLM的能力和任務複雜性動態調整的重要性。

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：根據需要進行分解和規劃與語言模型

ADaPT: As-Needed Decomposition and Planning with Language Models

摘要

Support