Metraipolis › archive › dc_004aedff1abd

Pulse: Long-Horizon Tasks Need Streaming Personalization — arXiv:2611.00988

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00988
License (as archived): CC0-1.0
Archived: 2026-11-03T10:42:10.455Z
SHA-256 of the archived text: 936bdb652369bdc3bfd356561d07fe4409654a6b8eb58178d836136d6358f399
Stable URL of this page: https://metraipolis.com/documento/dc_004aedff1abd

How to cite

Pulse: Long-Horizon Tasks Need Streaming Personalization — arXiv:2611.00988 — arXiv (en), https://arxiv.org/abs/2611.00988 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_004aedff1abd (Metraipolis archive dc_004aedff1abd, sha256 936bdb652369bdc3bfd356561d07fe4409654a6b8eb58178d836136d6358f399)

BibTeX

@misc{dc004aedff1abd,
  title = {Pulse: Long-Horizon Tasks Need Streaming Personalization — arXiv:2611.00988},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00988},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_004aedff1abd; sha256 936bdb652369bdc3bfd356561d07fe4409654a6b8eb58178d836136d6358f399},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00988. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents increasingly undertake complex, long-horizon tasks that benefit from sustained personalized support through long-term memory. Existing memory-augmented methods retrieve and use memory primarily from the initial request, with limited awareness of ongoing execution and emerging personalization needs. Agents may therefore overlook user preferences and project constraints during multistep tasks. We propose Pulse, a streaming personalization method for long-horizon tasks. An independent, lightweight memory agent continuously monitors execution, identifies emerging personalization needs and potential preference conflicts, and uses user and project memories to provide targeted interventions at appropriate stages. Reinforcement learning optimizes when and how the memory agent intervenes, improving the timeliness and accuracy of personalized support. Pulse scores 71.9% on $\pi$-Bench and 46.4% on MCP-Persona, achieving the highest overall scores among the compared methods on both datasets while improving task execution efficiency.

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/2611.00988 — 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 2026-11-03T10:39:50.205Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).