ADaPT: As-Needed Decomposition and Planning with Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Prasad, Archiki, Koller, Alexander, Hartmann, Mareike, Clark, Peter, Sabharwal, Ashish, Bansal, Mohit, Khot, Tushar
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917633916403712
author Prasad, Archiki
Koller, Alexander
Hartmann, Mareike
Clark, Peter
Sabharwal, Ashish
Bansal, Mohit
Khot, Tushar
author_facet Prasad, Archiki
Koller, Alexander
Hartmann, Mareike
Clark, Peter
Sabharwal, Ashish
Bansal, Mohit
Khot, Tushar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_05772
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ADaPT: As-Needed Decomposition and Planning with Language Models
Prasad, Archiki
Koller, Alexander
Hartmann, Mareike
Clark, Peter
Sabharwal, Ashish
Bansal, Mohit
Khot, Tushar
Artificial Intelligence
Computation and Language
Machine Learning
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.
title ADaPT: As-Needed Decomposition and Planning with Language Models
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2311.05772