Abstraction Generation for Generalized Planning with Pretrained Large Language Models

TL;DR

This paper explores using large language models to generate and refine qualitative numerical planning abstractions for generalized planning, demonstrating that with automated debugging, LLMs can produce useful abstractions.

Contribution

It introduces a prompt protocol and automated debugging method enabling LLMs to generate and improve QNP abstractions for generalized planning tasks.

Findings

LLMs can generate useful QNP abstractions with proper guidance.

Automated debugging effectively detects and corrects abstraction errors.

Guided LLMs outperform unguided approaches in abstraction quality.

Abstract

Qualitative Numerical Planning (QNP) serves as an important abstraction model for generalized planning (GP), which aims to compute general plans that solve multiple instances at once. Recent works show that large language models (LLMs) can function as generalized planners. This work investigates whether LLMs can serve as QNP abstraction generators for GP problems and how to fix abstractions via automated debugging. We propose a prompt protocol: input a GP domain and training tasks to LLMs, prompting them to generate abstract features and further abstract the initial state, action set, and goal into QNP problems. An automated debugging method is designed to detect abstraction errors, guiding LLMs to fix abstractions. Experiments demonstrate that under properly guided by automated debugging, some LLMs can generate useful QNP abstractions.