An evidence-driven method that records user feedback in temporal and activity-semantic bins outperforms LLM self-improvement methods for proactive interaction timing on a simulated assistant benchmark.
Nature , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants
An evidence-driven method that records user feedback in temporal and activity-semantic bins outperforms LLM self-improvement methods for proactive interaction timing on a simulated assistant benchmark.