{"ID":5675123,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T04:25:12.31577563Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01692","arxiv_id":"2607.01692","title":"From Answer Generators to Reasoning Facilitators: Designing AI Tutors for Mathematical Reasoning in High-Stakes Environments","abstract":"The rapid integration of Large Language Models (LLMs) into educational technology threatens to reduce mathematical learning to mere answer generation. This paper presents a generative study, usability study, and 12-participant field deployment of AITutor, an interactive system that translates theoretical pedagogical mechanisms into concrete user interface features. We explore how junior-high students preparing for high-stakes exams (Zhongkao) interact with AI tutoring. Through mixed-methods triangulation (7,379 telemetry events, 8 contextual observations, 10 interviews), we reveal that students actively resist traditional Socratic dialogue under time pressure, repurposing \"answer-first\" shortcuts as vital diagnostic checkpoints. We demonstrate how features like layered worked examples, step-linked visual grounding, and metacognitive scaffolding lower the interaction cost of reasoning repair. We contribute a \"Reasoning-Centered Product Loop,\" offering actionable implications for designing AI that structurally supports the inspection, local repair, curriculum verification, and delayed retrieval of mathematical reasoning in the wild.","short_abstract":"The rapid integration of Large Language Models (LLMs) into educational technology threatens to reduce mathematical learning to mere answer generation. This paper presents a generative study, usability study, and 12-participant field deployment of AITutor, an interactive system that translates theoretical pedagogical me...","url_abs":"https://arxiv.org/abs/2607.01692","url_pdf":"https://arxiv.org/pdf/2607.01692v1","authors":"[\"Yuming Feng\",\"Yuan Tian\",\"Erica Zhao\"]","published":"2026-07-02T04:36:33Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}