Metraipolis › archive › dc_6400876b976c
Just-in-Time Skill Retrieval via Long-Horizon State Tracking — arXiv:2611.01701
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01701
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:42:24.575Z
- SHA-256 of the archived text
f932c8685ba872622147e95610214dd401739773471bfa7875bfd74fb4b5978a- Stable URL of this page
https://metraipolis.com/documento/dc_6400876b976c
How to cite
Just-in-Time Skill Retrieval via Long-Horizon State Tracking — arXiv:2611.01701 — arXiv (en), https://arxiv.org/abs/2611.01701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6400876b976c (Metraipolis archive dc_6400876b976c, sha256 f932c8685ba872622147e95610214dd401739773471bfa7875bfd74fb4b5978a)
BibTeX
@misc{dc6400876b976c,
title = {Just-in-Time Skill Retrieval via Long-Horizon State Tracking — arXiv:2611.01701},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01701},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6400876b976c; sha256 f932c8685ba872622147e95610214dd401739773471bfa7875bfd74fb4b5978a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly rely on external skill libraries to support complex task execution. However, determining which skills are needed remains challenging in long-horizon tasks. Existing methods typically select a fixed skill set before execution, implicitly assuming that a task's procedural requirements can be determined from its initial description. This assumption is restrictive for long-horizon interaction, where new requirements emerge from intermediate observations, execution outcomes, and newly revealed constraints. This motivates just-in-time skill retrieval, which dynamically selects skills as execution unfolds. Just-in-time skill retrieval is promising but challenging: the utility of a skill depends not only on the current context, but also on the evolving task state shaped by prior steps. To this end, we propose JitSkill, a state-grounded framework that addresses this challenge through continuous task-state tracking. By connecting emerging requirements with accumulated task progress, JitSkill provides procedural support throughout execution without treating each retrieval decision independently. Experiments across three agent benchmarks demonstrate its effectiveness in improving long-horizon task completion. Our code is available at this https URL . 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/2611.01701 — 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 2026-11-03T10:39:50.237Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).