GenePlan: Evolving Better Generalized PDDL Plans Using Large Language Models
Proceedings of the International Conference on Automated Planning and Scheduling · 08.06.2026 · 36 (1) · 667-676
DOI: 10.1609/icaps.v36i1.42885 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International Conference on Automated Planning and Scheduling, online erschienen am 08.06.2026. Verfasst von Andrew Murray und 3 weiteren Autor:innen.
Abstract (Originalsprache)
We present GenePlan (GENeralized Evolutionary Planner), a novel framework that leverages large language model (LLM) assisted evolutionary algorithms to generate domain-dependent generalized planners for classical planning tasks described in PDDL. By casting generalized planning as an optimization problem, GenePlan iteratively evolves interpretable Python planners that minimize plan length across diverse problem instances. In empirical evaluation across six existing benchmark domains and two new domains, GenePlan achieved an average SAT score of 0.91, closely matching the performance of the state-of-the-art planners (SAT score 0.93), and significantly outperforming other LLM-based baselines such as chain-of-thought prompting (average SAT score 0.64). The generated planners solve new instances rapidly (average 0.49 seconds per task) and at low cost (average $1.82 per domain using GPT-4o).
Zitieren
APA
Murray, A., Dervovic, D., Pozanco, A., & Cashmore, M. (2026). GenePlan: Evolving Better Generalized PDDL Plans Using Large Language Models. Proceedings of the International Conference on Automated Planning and Scheduling, 36(1), 667-676. https://doi.org/10.1609/icaps.v36i1.42885
Vancouver
Murray A, Dervovic D, Pozanco A, Cashmore M. GenePlan: Evolving Better Generalized PDDL Plans Using Large Language Models. Proceedings of the International Conference on Automated Planning and Scheduling. 2026;36(1):667-676. doi:10.1609/icaps.v36i1.42885
BibTeX
@article{Murray2026,
author = {Murray, Andrew and Dervovic, Danial and Pozanco, Alberto and Cashmore, Michael},
title = {GenePlan: Evolving Better Generalized PDDL Plans Using Large Language Models},
journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
year = {2026},
volume = {36},
number = {1},
pages = {667--676},
doi = {10.1609/icaps.v36i1.42885}
}
EUVIMED