Saved in:
Bibliographic Details
Main Authors: Caglar, Turgay, Belhaj, Sirine, Chakraborti, Tathagata, Katz, Michael, Sreedharan, Sarath
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.13720
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914701707837440
author Caglar, Turgay
Belhaj, Sirine
Chakraborti, Tathagata
Katz, Michael
Sreedharan, Sarath
author_facet Caglar, Turgay
Belhaj, Sirine
Chakraborti, Tathagata
Katz, Michael
Sreedharan, Sarath
contents This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems that have been studied in the AI planning literature and explore the effect of an LLM on those tasks. We empirically demonstrate how the performance of an LLM contrasts with combinatorial search (CS) -- an approach that has been traditionally used to solve model space tasks in planning, both with the LLM in the role of a standalone model space reasoner as well as in the role of a statistical signal in concert with the CS approach as part of a two-stage process. Our experiments show promising results suggesting further forays of LLMs into the exciting world of model space reasoning for planning tasks in the future.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13720
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning
Caglar, Turgay
Belhaj, Sirine
Chakraborti, Tathagata
Katz, Michael
Sreedharan, Sarath
Artificial Intelligence
This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems that have been studied in the AI planning literature and explore the effect of an LLM on those tasks. We empirically demonstrate how the performance of an LLM contrasts with combinatorial search (CS) -- an approach that has been traditionally used to solve model space tasks in planning, both with the LLM in the role of a standalone model space reasoner as well as in the role of a statistical signal in concert with the CS approach as part of a two-stage process. Our experiments show promising results suggesting further forays of LLMs into the exciting world of model space reasoning for planning tasks in the future.
title Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning
topic Artificial Intelligence
url https://arxiv.org/abs/2311.13720