# Abstraction Generation for Generalized Planning with Pretrained Large Language Models

arXiv: https://arxiv.org/abs/2602.10485 · HTML: https://mlsanity.com/paper/2602.10485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023)
- [Features, Projections, and Representation Change for Generalized Planning](https://mlsanity.com/paper/1801.10055/) (2018)
- [Generalized Planning With Procedural Domain Control Knowledge](https://mlsanity.com/paper/1910.04999/) (2019)
- [First-Order Logic with Counting: At Least, Weak Hanf Normal Forms Always Exist and Can Be Computed!](https://mlsanity.com/paper/1703.01122/) (2017)
- [Guarantees for Sound Abstractions for Generalized Planning (Extended Paper)](https://mlsanity.com/paper/1905.12071/) (2019)
- [Using Large Language Models for Abstraction of Planning Domains - Extended Version](https://mlsanity.com/paper/2510.20258/) (2025)

## Abstract (arXiv)

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.