ADaPT: As-Needed Decomposition and Planning with Language Models

arXiv:2311.05772v2 Announce Type: replace-cross
Abstract: 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 …

abstract adapt agents arxiv cs.ai cs.cl cs.lg decision environment however interactive iterative language language models large language large language models llms making next planning struggle tasks the environment type