When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks
A decision-theoretic model is developed to determine time-efficient confirmation point placement and results show that 81% of participants preferred the intermediate confirmation approach over the confirm-at-end approach used by existing systems, and task completion time was reduced by 13.54%.
Jie-Yu Zhou, Aryan Roy, Sneh Gupta et al.
· International Conference on... · 7 citations
· ⚡2