{"ID":3084779,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T02:02:03.244594148Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05602","arxiv_id":"2606.05602","title":"Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap Localization","abstract":"AI assistants in human-AI collaboration often correct suboptimal human actions through behavioral feedback (e.g., alerts or steering-wheel nudges in assistive driving). Such interventions can mitigate immediate errors, but long-term improvement requires addressing the underlying misconceptions that cause repeated mistakes. We introduce SENSEI, a framework that infers user misconceptions from interaction behavior and provides targeted, minimal yet sufficient suggestions to correct them. Our approach departs from action- or trajectory-level interventions by operating over a structured knowledge representation to localize and correct the sources of erroneous behavior. Across three long-horizon tasks with diverse misconceptions and corresponding behaviors, SENSEI demonstrates zero-shot compositional generalization, disentangling multiple overlapping misconceptions despite training only on single-misconception cases. A user study further shows that our method identifies real human misconceptions and provides effective guidance that improves long-horizon task performance, successfully correcting $90\\%$ of student misconceptions. Code and project page are available at https://misoshiruseijin.github.io/SENSEI/.","short_abstract":"AI assistants in human-AI collaboration often correct suboptimal human actions through behavioral feedback (e.g., alerts or steering-wheel nudges in assistive driving). Such interventions can mitigate immediate errors, but long-term improvement requires addressing the underlying misconceptions that cause repeated mista...","url_abs":"https://arxiv.org/abs/2606.05602","url_pdf":"https://arxiv.org/pdf/2606.05602v1","authors":"[\"Ayano Hiranaka\",\"Ya-Chuan Hsu\",\"Stefanos Nikolaidis\",\"Erdem Bıyık\",\"Daniel Seita\"]","published":"2026-06-04T02:25:19Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.HC\",\"cs.LG\"]","methods":"[]","has_code":false}