Metraipolis › archive › dc_cc5aedeb6bdf

MemoWM: How World Models Change What Agents Need to Remember — arXiv:2610.10778

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.10778
License (as archived): CC0-1.0
Archived: 2026-10-09T05:55:57.349Z
SHA-256 of the archived text: d2483efbf33b17da6293f705f0b65713ce724353ce9a0c9944ae1aabc9c335da
Stable URL of this page: https://metraipolis.com/documento/dc_cc5aedeb6bdf

How to cite

MemoWM: How World Models Change What Agents Need to Remember — arXiv:2610.10778 — arXiv (en), https://arxiv.org/abs/2610.10778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc5aedeb6bdf (Metraipolis archive dc_cc5aedeb6bdf, sha256 d2483efbf33b17da6293f705f0b65713ce724353ce9a0c9944ae1aabc9c335da)

BibTeX

@misc{dccc5aedeb6bdf,
  title = {MemoWM: How World Models Change What Agents Need to Remember — arXiv:2610.10778},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10778},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc5aedeb6bdf; sha256 d2483efbf33b17da6293f705f0b65713ce724353ce9a0c9944ae1aabc9c335da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-term agents face growing storage demands as they accumulate experience. World models capture reusable regularities that can reduce the information stored for each experience. We formulate the problem of memory allocation conditioned on a world model and introduce MemoWM, a framework that uses shared predictions to compress retained information and reconstruct omitted content. Its task-aware allocation rule balances the expected impact of reconstruction errors against storage cost, retaining information with downstream value beyond the predictive prior. Across five long-term agent-memory benchmarks, MemoWM achieves 42.42\% average answer accuracy, exceeding the strongest baseline by 2.62 percentage points, while reducing average experience-specific storage by 53.9\% relative to MIRIX, the most storage-efficient baseline. Further analysis shows that stronger world models reduce per-experience storage at comparable task quality. Accounting for model parameters reveals a trade-off between shared model capacity and recurring storage costs, with the capacity that minimizes total storage increasing as more interactions are retained. 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: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.10778 — 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 2026-10-09T05:47:01.316Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).