Communication Dans Un Congrès Année : 2026

A decision-theoretic representation of assistive interfaces

Résumé

Assistive interfaces, such as recommendation engines, adaptive systems, and intelligent assistants, span diverse methods and disci- plines but lack a shared conceptual foundation. This paper models assistance as sequential decision-making under uncertainty between two agents: the user and the assistant. The formalism allows casting assistance as an optimization problem and offers a rich but principled vocabulary to understand the dynamics of assistance. Drawing on Partially Observable Stochastic Games (POSGs) and related models, we: (1) motivate multi-agent over single-agent for- mulations; (2) adapt POSGs to HCI and clarify their tractability through reductions; (3) propose a two-agent sequential model that unambiguously defines concepts such as adaptation, augmentation, and delegation; (4) illustrate applicability through domain prob- lems and examples; and (5) offer a supporting implementation via a library. These results warrant more attention on decision-theory as a principled yet actionable approach to assistive interfaces.

Fichier principal
Vignette du fichier
main_manuscript.pdf (882.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05600927 , version 1 (11-05-2026)

Licence

Identifiants

Citer

Julien Gori, Aurelien Nioche, Christoph Johns, Antti Oulasvirta. A decision-theoretic representation of assistive interfaces. CHI 2026: CHI Conference on Human Factors in Computing Systems, Apr 2026, Barcelona, Spain. pp.1-19, ⟨10.1145/3772318.3791819⟩. ⟨hal-05600927⟩
2 Consultations
0 Téléchargements

Altmetric

Partager

  • More