Metraipolis › archive › dc_bef409cc156a

HGP:An on-device personalized agent memory via hybrid graph storage — arXiv:2610.10071

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10071
License (as archived)
CC0-1.0
Archived
2026-10-08T11:09:44.560Z
SHA-256 of the archived text
fd77d1da349bd87728326fb1e45142edee2ccd4c21de3258106f9ecb5666c6c7
Stable URL of this page
https://metraipolis.com/documento/dc_bef409cc156a

How to cite

HGP:An on-device personalized agent memory via hybrid graph storage — arXiv:2610.10071 — arXiv (en), https://arxiv.org/abs/2610.10071 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bef409cc156a (Metraipolis archive dc_bef409cc156a, sha256 fd77d1da349bd87728326fb1e45142edee2ccd4c21de3258106f9ecb5666c6c7)
BibTeX
@misc{dcbef409cc156a,
  title = {HGP:An on-device personalized agent memory via hybrid graph storage — arXiv:2610.10071},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10071},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bef409cc156a; sha256 fd77d1da349bd87728326fb1e45142edee2ccd4c21de3258106f9ecb5666c6c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10071. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based agents face challenges in personalized interactive tasks due to heterogeneous, multi-typed, and implicitly constrained long-term traces. Existing memory mechanisms struggle with accurate routing and retrieval, especially on-device where personalization is critical. Most methods use single-vector representations, blurring type distinctions and relational structure. We propose HGP, a hybrid graph memory framework. HGP employs a lightweight self-enhancement classifier for personalized memory routing and constructs episodic, semantic, and procedural memories as graphs. It also extracts working memory as a state trajectory to capture current state and implicit constraints, ensuring reliable decision-making. The classifier reduces large-model calls, enabling on-device deployment, while graph storage enables accurate retrieval and incremental user profile refinement. Experiments on two benchmarks show that on PAL-Set solution selection, HGP achieves an S-score of 35.58, nearly 7 points above the strongest baseline. Code and data are 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/2610.10071 — 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 2026-10-08T10:14:05.973Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).