Metraipolis › archive › dc_3a034149338a

When the Past Shapes Action: Understanding Embodied Memory — arXiv:2610.41688

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41688
License (as archived): CC0-1.0
Archived: 2026-11-03T07:52:40.362Z
SHA-256 of the archived text: 8c3409273b97811235fab8de25a67434ac432c18b3b941e584285e321e154aad
Stable URL of this page: https://metraipolis.com/documento/dc_3a034149338a

How to cite

When the Past Shapes Action: Understanding Embodied Memory — arXiv:2610.41688 — arXiv (en), https://arxiv.org/abs/2610.41688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a034149338a (Metraipolis archive dc_3a034149338a, sha256 8c3409273b97811235fab8de25a67434ac432c18b3b941e584285e321e154aad)

BibTeX

@misc{dc3a034149338a,
  title = {When the Past Shapes Action: Understanding Embodied Memory — arXiv:2610.41688},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41688},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a034149338a; sha256 8c3409273b97811235fab8de25a67434ac432c18b3b941e584285e321e154aad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation. We organize existing approaches along two complementary dimensions: six fundamental memory requirements, spanning world-state persistence, task progress, belief maintenance, and experiential learning; and eight architectural categories, including recurrent states, fast weights, visual and symbolic representations, spatial memory, and experience-based systems. We analyze their capabilities and limitations, and examine how existing benchmarks evaluate memory-dependent behavior, distinguishing genuine use of historical information from general task performance. Finally, we identify open challenges in selecting relevant experiences, maintaining consistent beliefs in changing environments, and consolidating knowledge across episodes. Our analysis provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41688 — 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 2026-11-03T07:49:31.169Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).