Metraipolis › archive › dc_16bf8bcc0843
Curriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience — arXiv:2610.34677
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34677
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:57:37.404Z
- SHA-256 of the archived text
a06d85b9c4f66be827ddb7cf08959d7dca6affd6c1a3fbd4f93b2572e81281bd- Stable URL of this page
https://metraipolis.com/documento/dc_16bf8bcc0843
How to cite
Curriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience — arXiv:2610.34677 — arXiv (en), https://arxiv.org/abs/2610.34677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16bf8bcc0843 (Metraipolis archive dc_16bf8bcc0843, sha256 a06d85b9c4f66be827ddb7cf08959d7dca6affd6c1a3fbd4f93b2572e81281bd)
BibTeX
@misc{dc16bf8bcc0843,
title = {Curriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience — arXiv:2610.34677},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34677},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16bf8bcc0843; sha256 a06d85b9c4f66be827ddb7cf08959d7dca6affd6c1a3fbd4f93b2572e81281bd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hierarchical task knowledge enables efficient problem solving by allowing previously acquired skills to be reused across tasks and problem instances. In this paper, we investigate curriculum-guided acquisition of hierarchical task knowledge in an HTN learning framework. We compare three approaches: online learning during problem solving, human-designed curricula, and an automated curriculum generation procedure that derives learning experiences from verified LLM-generated solution traces. The proposed procedure solves small training problems with an LLM, extracts task accomplishment information, and transforms it into ordered sequences of state-task learning problems for HTN method acquisition. We evaluate the three approaches across multiple planning domains. The results demonstrate that automatically generated curricula recover much of the benefit of expert-designed curricula while substantially reducing the token cost of online hierarchical knowledge acquisition. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.34677 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.698Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).