STARS: extending interactive task learning with large language models
Frontiers in Computer Science · 04.08.2026 · 8
DOI: 10.3389/fcomp.2026.1848830 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Computer Science, online erschienen am 04.08.2026. Verfasst von James R. Kirk und 2 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Office of Naval Research.
Abstract (Originalsprache)
Interactive Task Learning (ITL) enables cognitive agents to learn novel tasks (in one shot) from natural-language instruction and allows humans to customize agents to align with individual preferences. ITL relies on reasoning over and learning from multiple sources of knowledge, a strength of cognitive architectures. However, ITL requires frequent human input, which can be tedious and time-consuming. We evaluate large language models (LLMs) as an additional source of knowledge for ITL. We summarize initial experiments exploring the potential use of LLMs in ITL and then describe a novel method (STARS) that markedly improves the reliability of task learning from LLMs for embodied ITL agents. We demonstrate that LLMs speed agent learning and greatly reduce the human effort required to achieve robust, reliable, and repeatable task performance.
Förderung
- Office of Naval Research
Zitieren
APA
Kirk, J. R., Wray, R. E., & Laird, J. E. (2026). STARS: extending interactive task learning with large language models. Frontiers in Computer Science, 8. https://doi.org/10.3389/fcomp.2026.1848830
Vancouver
Kirk JR, Wray RE, Laird JE. STARS: extending interactive task learning with large language models. Frontiers in Computer Science. 2026;8. doi:10.3389/fcomp.2026.1848830
BibTeX
@article{Kirk2026,
author = {Kirk, James R. and Wray, Robert E. and Laird, John E.},
title = {STARS: extending interactive task learning with large language models},
journal = {Frontiers in Computer Science},
year = {2026},
volume = {8},
doi = {10.3389/fcomp.2026.1848830}
}
EUVIMED