Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight
This addresses the challenge of designing responsible AI agents for human-AI partnerships, but it is incremental as it builds on existing theories without presenting new empirical results.
The paper tackles the problem that generative AI agents assume users can articulate their needs, which fails when users are unaware of missing or risky information, and argues that proactivity must be grounded in epistemic and behavioral principles to avoid harmful interventions.
Generative AI agents equate understanding with resolving explicit queries, an assumption that confines interaction to what users can articulate. This assumption breaks down when users themselves lack awareness of what is missing, risky, or worth considering. In such conditions, proactivity is not merely an efficiency enhancement, but an epistemic necessity. We refer to this condition as epistemic incompleteness: where progress depends on engaging with unknown unknowns for effective partnership. Existing approaches to proactivity remain narrowly anticipatory, extrapolating from past behavior and presuming that goals are already well defined, thereby failing to support users meaningfully. However, surfacing possibilities beyond a user's current awareness is not inherently beneficial. Unconstrained proactive interventions can misdirect attention, overwhelm users, or introduce harm. Proactive agents, therefore, require behavioral grounding: principled constraints on when, how, and to what extent an agent should intervene. We advance the position that generative proactivity must be grounded both epistemically and behaviorally. Drawing on the philosophy of ignorance and research on proactive behavior, we argue that these theories offer critical guidance for designing agents that can engage responsibly and foster meaningful partnerships.