Generating consistent PDDL domains with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Smirnov, Pavel, Joublin, Frank, Ceravola, Antonello, Gienger, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917637273944064
author Smirnov, Pavel
Joublin, Frank
Ceravola, Antonello
Gienger, Michael
author_facet Smirnov, Pavel
Joublin, Frank
Ceravola, Antonello
Gienger, Michael
contents Large Language Models (LLMs) are capable of transforming natural language domain descriptions into plausibly looking PDDL markup. However, ensuring that actions are consistent within domains still remains a challenging task. In this paper we present a novel concept to significantly improve the quality of LLM-generated PDDL models by performing automated consistency checking during the generation process. Although the proposed consistency checking strategies still can't guarantee absolute correctness of generated models, they can serve as valuable source of feedback reducing the amount of correction efforts expected from a human in the loop. We demonstrate the capabilities of our error detection approach on a number of classical and custom planning domains (logistics, gripper, tyreworld, household, pizza).
format Preprint
id arxiv_https___arxiv_org_abs_2404_07751
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generating consistent PDDL domains with Large Language Models
Smirnov, Pavel
Joublin, Frank
Ceravola, Antonello
Gienger, Michael
Robotics
Artificial Intelligence
Large Language Models (LLMs) are capable of transforming natural language domain descriptions into plausibly looking PDDL markup. However, ensuring that actions are consistent within domains still remains a challenging task. In this paper we present a novel concept to significantly improve the quality of LLM-generated PDDL models by performing automated consistency checking during the generation process. Although the proposed consistency checking strategies still can't guarantee absolute correctness of generated models, they can serve as valuable source of feedback reducing the amount of correction efforts expected from a human in the loop. We demonstrate the capabilities of our error detection approach on a number of classical and custom planning domains (logistics, gripper, tyreworld, household, pizza).
title Generating consistent PDDL domains with Large Language Models
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2404.07751