Metraipolis › archive › dc_c8193858dfd3

Before Bringing It Up: When and How AI Companions Should Use Memor — arXiv:2610.09470

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09470
License (as archived): CC0-1.0
Archived: 2026-10-08T11:55:38.580Z
SHA-256 of the archived text: ee344bcd5a32a0f79460418d5f42d4ef10deb185c8d6f7fb67dd0430f284d14a
Stable URL of this page: https://metraipolis.com/documento/dc_c8193858dfd3

How to cite

Before Bringing It Up: When and How AI Companions Should Use Memor — arXiv:2610.09470 — arXiv (en), https://arxiv.org/abs/2610.09470 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8193858dfd3 (Metraipolis archive dc_c8193858dfd3, sha256 ee344bcd5a32a0f79460418d5f42d4ef10deb185c8d6f7fb67dd0430f284d14a)

BibTeX

@misc{dcc8193858dfd3,
  title = {Before Bringing It Up: When and How AI Companions Should Use Memor — arXiv:2610.09470},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09470},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8193858dfd3; sha256 ee344bcd5a32a0f79460418d5f42d4ef10deb185c8d6f7fb67dd0430f284d14a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09470. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory can sustain AI companionship, yet even accurate recollection can be inappropriate to use. Two rounds of formative interviews with 14 users (n = 6 exploratory, n = 8 memory-focused) motivate asking what a companion should consider before using past information. Eight themes inform Reconsider, a single-call procedure with five checks and four handling modes, evaluated on 80 scenarios across five models over 400 blinded within-model pairs. Two LLM judges favored Reconsider by net margins of +15 and +23 percentage points, with bootstrap intervals excluding zero for three of five models but not for GPT or Claude. Evaluator analysis linked judge scoring differences to model family, and a preliminary matched-guidance control isolating memory-specific content gave positive margins. We contribute an interview-grounded design framework for memory use and an evaluation that scrutinizes its own evaluators.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.09470 — 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 2026-10-08T10:50:22.553Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).