Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight
Kirandeep Kaur, Xingda Lyu, Chirag Shah

TL;DR
This paper argues that generative AI agents should be re-grounded in epistemic and behavioral principles to effectively support users' unknowns and avoid harmful overreach, moving beyond simple query resolution.
Contribution
It introduces a framework emphasizing epistemic incompleteness and behavioral constraints to improve proactive AI interactions, grounded in philosophical and behavioral theories.
Findings
Proactive AI needs to address unknown unknowns for effective partnership.
Unconstrained interventions can mislead or overwhelm users.
Grounding proactivity in epistemic and behavioral principles enhances responsible AI design.
Abstract
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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEthics and Social Impacts of AI · Explainable Artificial Intelligence (XAI) · Embodied and Extended Cognition
