Knowledge Engineering for Planning and Scheduling in the LLM Era

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10512214" target="_blank" >RIV/00216208:11320/25:10512214 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21730/25:00386272
Result on the web
<a href="https://doi.org/10.1609/icaps.v35i1.36142" target="_blank" >https://doi.org/10.1609/icaps.v35i1.36142</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/icaps.v35i1.36142" target="_blank" >10.1609/icaps.v35i1.36142</a>

Result language
angličtina
Original language name
Knowledge Engineering for Planning and Scheduling in the LLM Era
Original language description
Automated planning requires explicit domain knowledge to generate effective solutions. The process of formulating, maintaining, and validating this knowledge is the cornerstone of Knowledge Engineering for Planning and Scheduling (KEPS). Although Large Language Models (LLMs) have shown promise for automated planning tasks, and are gaining popularity in the field, their impact on KEPS remains under-explored. In this paper, we investigate the potential of LLMs to streamline and enhance the KEPS field by taking a close look at the processes used to develop explicit symbolic knowledge models, in particular for use in safety-related applications. The paper's findings are that while LLMs can assist in knowledge acquisition and formulation, human domain expertise and external symbolic validators remain indispensable for ensuring correctness, operationality and completeness of planning applications.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project
<a href="/en/project/GA25-18003S" target="_blank" >GA25-18003S: Using formal grammars and automata to acquire and verify domain control knowledge in planning</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings International Conference on Automated Planning and Scheduling Icaps
ISBN
978-1-57735-903-6
ISSN
2334-0835
e-ISSN
2334-0843
Number of pages
5
Pages from-to
391-395
Publisher name
AAAI Press
Place of publication
Washington DC, USA
Event location
Melbourne
Event date
Nov 9, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)