Metraipolis › archive › dc_675f72bb6fbd
Reliable Knowledge Acquisition for Continual Learning Agents — arXiv:2610.21739
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21739
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:28:39.839Z
- SHA-256 of the archived text
6a3c7ca98904350f4abebd3a0cd29922c2a526fe3a95abb8c5129ce46a0a472d- Stable URL of this page
https://metraipolis.com/documento/dc_675f72bb6fbd
How to cite
Reliable Knowledge Acquisition for Continual Learning Agents — arXiv:2610.21739 — arXiv (en), https://arxiv.org/abs/2610.21739 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_675f72bb6fbd (Metraipolis archive dc_675f72bb6fbd, sha256 6a3c7ca98904350f4abebd3a0cd29922c2a526fe3a95abb8c5129ce46a0a472d)
BibTeX
@misc{dc675f72bb6fbd,
title = {Reliable Knowledge Acquisition for Continual Learning Agents — arXiv:2610.21739},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21739},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_675f72bb6fbd; sha256 6a3c7ca98904350f4abebd3a0cd29922c2a526fe3a95abb8c5129ce46a0a472d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21739. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on models with fixed parameters, this learning requires reusing prior task experience in context to improve performance and efficiency on future tasks. Existing memory and experience-learning systems typically focus on either retained facts or procedures, and lack a mechanism for establishing the reliability of claims extracted from the ongoing task stream. Indeed, we find that approximately 12--33\% of entries produced by representative systems harm future task performance when reused. To address these limitations, we propose \textbf{RIKA} (Reliable Knowledge Acquisition), which combines hierarchical extraction of factual, conceptual, procedural, and metacognitive knowledge with Evidence-based Knowledge Admission, which uses source evidence and subsequent experience to govern which claims enter the task agent's context, without additional validation tasks. Across six task streams from Continual Learning Bench and four model backbones, RIKA achieves the highest aggregate score on every backbone.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21739 — 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 2026-10-16T08:44:17.990Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).