Line of inquiry
Inquiring lines›How do language models learn and r…›What enables language models to co…›this line of inquiry
How can agents discover and adapt to user preferences during conversation?
A broader line of inquiry — a family of 43 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 43
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- How can agents learn user preferences during conversation without pre-calibration?
- Can curiosity reward during conversation compete with simulated interaction optimization for alignment?
- How can agents learn to estimate user satisfaction in real-time during conversation?
- Can AI systems distinguish between users' stated preferences and their genuine long-term interests?
- Can curiosity-driven personalization work better than pre-conversation preference elicitation?
- When should agents accommodate user preferences over their own goals?
- Can curiosity-driven dialogue incrementally discover user interest journeys in real time?
- How can dialogue structure and trajectory predict social agent performance?
- What role does uncertainty reduction play in personalized agent interaction?
- Why might text-only interfaces underestimate agent preference elicitation capabilities?
- Can agents balance goal-driven proactivity with user preference alignment?
- How does multi-turn dialogue improve user satisfaction in search interactions?
- How should conversational recommender systems balance task focus with rapport building?
- How do attribute-asking strategies depend on current confidence in candidate items?
- Can preference-elicitation dialogue simulators generate sociable recommendation strategies?
- How do insert-expansions help systems probe users before silently diverging?
- Can mention sequences exploit shortcuts like repeated items rather than learning genuine preferences?
- How do expectation-management metrics differ from traditional conversational quality metrics?
- How can agents detect whether users are willing to follow their topic guidance?
- Can systems guide users adaptively without imposing predetermined dialogue structures?
- Can curiosity rewards about user type complement general social motivation frameworks?
- What interaction history signals indicate what a participant finds relevant?
- Does sequential structure within sessions complement cross-session preference channels?
- How well do user simulators trained from real dialogue predict actual user satisfaction?
- What multi-turn reward structures would encourage active intent discovery?
- What role does conversation state tracking play in timing ask versus recommend?
- Can sequential modeling of conversation history exploit the repeated-item shortcut at scale?
- Do people with lower cognitive complexity prefer simpler machine communication goals?
- Can elicited user responses measure true preferences or just elicitation artifacts?
- Why do abstract semantic memories outperform specific interaction histories for journey discovery?
- How does active learning reduce queries needed for user preference inference?
- How do humans decide when to contribute to group conversations?
- Can personalized questions improve conversation quality in open-domain chat?
- Do look-alike users help more when the current session is sparse or vague?
- Does adding survey data to interviews improve agent accuracy further?
- How does asymmetric information shape what to ask users first?
- How should ground truth labels be assigned to simulated user sessions?
- What structural signals in user language reveal their unstated preferences and context?
- How do social context features like user history extend politeness-based prediction models?
- Can agents learn user intent from unlabeled video without text labels?
- How should systems learn what each meeting participant actually cares about?
- How do direct and indirect similarity inference differ as paths to cooperation?
- How can insert-expansion techniques help users discover their own preferences?