Skip to content
arXiv cs.AI · Papers

Beyond expert users: agents should help users construct preferences, not just elicit them

arXiv:2606.30863v1 Announce Type: new Abstract: Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task is underspecified. We argue this assumption is unrealistic. Users often lack the domain knowledge to have completely sp