Metraipolis › archive › dc_6487f60475a3
Towards In-Parameter Memory Augmentation for Large Language Models — arXiv:2610.08630
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08630
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:23:26.641Z
- SHA-256 of the archived text
067d2a7961347586daede85f929db1be311c7b268a351e68e55f013246ea6661- Stable URL of this page
https://metraipolis.com/documento/dc_6487f60475a3
How to cite
Towards In-Parameter Memory Augmentation for Large Language Models — arXiv:2610.08630 — arXiv (en), https://arxiv.org/abs/2610.08630 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6487f60475a3 (Metraipolis archive dc_6487f60475a3, sha256 067d2a7961347586daede85f929db1be311c7b268a351e68e55f013246ea6661)
BibTeX
@misc{dc6487f60475a3,
title = {Towards In-Parameter Memory Augmentation for Large Language Models — arXiv:2610.08630},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08630},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6487f60475a3; sha256 067d2a7961347586daede85f929db1be311c7b268a351e68e55f013246ea6661},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08630. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. \textbf{In-parameter memory} offers a complementary substrate: reusable memory information is represented in model parameters, adapters, or other parameter-like objects that are composed into the forward pass at inference time. This survey focuses on methods that augment LLMs with such parametric memory at deployment: a memory-bearing parameter object is plugged into the forward pass during inference, whether it is acquired before or during deployment. We organize the landscape with two orthogonal axes: \textbf{Parameter Placement}, which includes Embedding, Attention, FFN layers, or Hybrid when two or more layers are used; and \textbf{Parameter Acquisition Time}, which distinguishes methods whose memory object is acquired during deployment (online) from those acquired before it (offline). We clarify boundaries, conduct comparisons, and discuss open directions in interference, safety, co-design with ICL, and recursive self-improvement.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.08630 — 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 2026-10-07T11:15:39.459Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).