Automating Thought of Search: A Journey Towards Soundness and Completeness
Proceedings of the International Conference on Automated Planning and Scheduling · 08.06.2026 · 36 (1) · 591-600
DOI: 10.1609/icaps.v36i1.42877 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International Conference on Automated Planning and Scheduling, online erschienen am 08.06.2026. Verfasst von Daniel Cao und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Large language models (LLMs) are being used to solve planning problems that require search. Most of the literature uses LLMs as world models to define the search space, forgoing soundness for the sake of flexibility. A recent work, Thought of Search (ToS), proposed defining the search space with code, having LLMs produce that code. ToS requires a human in the loop, collaboratively producing a sound successor function and goal test. The result, however, is worth the effort: all the tested datasets were solved with 100% accuracy. Consequently, there is great potential to automate the ToS process. We take a first major step towards automating ToS (AutoToS), taking the human out of the loop of interactions with the language model. AutoToS guides the language model step by step towards the generation of sound and complete search components, through feedback from both generic and domain specific unit tests. We show that AutoToS is able to achieve 100% accuracy on all the evaluated domains with a small number of LLM calls.
Zitieren
APA
Cao, D., Katz, M., Kokel, H., Srinivas, K., & Sohrabi, S. (2026). Automating Thought of Search: A Journey Towards Soundness and Completeness. Proceedings of the International Conference on Automated Planning and Scheduling, 36(1), 591-600. https://doi.org/10.1609/icaps.v36i1.42877
Vancouver
Cao D, Katz M, Kokel H, Srinivas K, Sohrabi S. Automating Thought of Search: A Journey Towards Soundness and Completeness. Proceedings of the International Conference on Automated Planning and Scheduling. 2026;36(1):591-600. doi:10.1609/icaps.v36i1.42877
BibTeX
@article{Cao2026,
author = {Cao, Daniel and Katz, Michael and Kokel, Harsha and Srinivas, Kavitha and Sohrabi, Shirin},
title = {Automating Thought of Search: A Journey Towards Soundness and Completeness},
journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
year = {2026},
volume = {36},
number = {1},
pages = {591--600},
doi = {10.1609/icaps.v36i1.42877}
}
EUVIMED