Metraipolis › archive › dc_56fffe4bde20

PresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User State — arXiv:2610.23625

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23625
License (as archived)
CC0-1.0
Archived
2026-10-19T08:43:19.449Z
SHA-256 of the archived text
9f0e67e877a8b95ac585ece0459efff4061af3aab348bb35ee4ad664149428df
Stable URL of this page
https://metraipolis.com/documento/dc_56fffe4bde20

How to cite

PresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User State — arXiv:2610.23625 — arXiv (en), https://arxiv.org/abs/2610.23625 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56fffe4bde20 (Metraipolis archive dc_56fffe4bde20, sha256 9f0e67e877a8b95ac585ece0459efff4061af3aab348bb35ee4ad664149428df)
BibTeX
@misc{dc56fffe4bde20,
  title = {PresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User State — arXiv:2610.23625},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23625},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56fffe4bde20; sha256 9f0e67e877a8b95ac585ece0459efff4061af3aab348bb35ee4ad664149428df},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23625. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Presence-aware intelligence is the capacity of an AI system's intelligence layer to adapt appropriately to the functional state of the person it serves (here readiness, flow, and stability) while preserving task quality and safety. We introduce PresenceBench, an instrument for measuring it. PresenceBench evaluates how the intelligence layer uses a supplied state, not how that state is sensed, and breaks the capability into measurable properties. Two are tested here. Receptivity: does the model take up the state and give a better response than with no signal? Specificity: does any improvement depend on the correct state, rather than on extra structured context? A third, adaptation across states, is a required endpoint not measured in this release. A five-arm causal design answers both questions, against each model's own baseline and an equally structured mismatched-state control, scored by a correctness-gated human paired comparison. The exploratory evaluation covered four models across eighteen single-turn, six fixed three-turn and six simulated natural-conversation scenarios. Supplying a synthetic state, raw or translated into a response policy, gave human-preference point estimates above 0.5 for all four models (Claude Sonnet 5, DeepSeek V4 Pro, Gemini 3.6 Flash, GPT-5.6 Terra), with three of eight 95% intervals excluding chance. Specificity was not resolved: no per-model interval excluded chance, and the design cannot yet separate the state values from a generic instruction to adapt. Policy delivery reduced priced cost and output tokens against each model's baseline; these are resource-use changes, not efficiency gains, because correctness non-inferiority was not established. Safety-floor failures were rare (13 of 360 cases), with a non-significant excess under policy delivery. We report the instrument, the frozen results, and the controls a confirmatory study needs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.23625 — 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 2026-10-19T08:39:10.162Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).