cs.AINov 17, 2026

VeriMath: Human-in-the-Loop Generation and Verification of Curriculum-Aligned Mathematics Assessment Items

Authors: Quy P. Nguyen, Duong Q. Nguyen, Dinh P. T. Nguyen, Truong-Giang T. Le, Truong A. Bui, Vi H. Vo, Quang-Thinh Bui, My-Phuong Ngo, 

Organizations: Center for AI Research, VinUniversity, Ho Chi Minh City, Viet Nam · An Lao High School, Gia Lai, Viet Nam · Chu Van An High School for Gifted Students, Gia Lai, Viet Nam · FPT Play, Ho Chi Minh City, Viet Nam · 

Abstract

Automatic generation of mathematics assessment items is a growing area in educational artificial intelligence, yet classroom deployment remains challenging. Generated questions must satisfy multiple constraints: mathematical correctness, curriculum alignment, appropriate cognitive difficulty, and educator reviewability. While prior work has advanced text generation, reliable assessment authoring requires granular control over localized examination formats and expert educational judgment. To address this challenge, we present VeriMath, a generalized, human-in-the-loop framework for generating rigorous, curriculum-constrained mathematics assessment drafts. Using annotated reference items, the framework anchors generation to the requested examination section and cognitive reasoning level, then applies sequential automated verification and guided repair before submitting drafts for expert review. We evaluate VeriMath through a national curriculum case study using 4,555 mathematics items from the Vietnamese Grade 12 curriculum and 50 distinct generation requirements covering multiple-choice, true/false, and short-answer formats. Across two model backbones, the framework produces verifier-accepted drafts for 94% (47/50) of requirements per run. Blind expert evaluations confirm high mathematical accuracy and curriculum alignment, with strict teacher-readiness assessments accepting up to 56.8% of generated items. Analysis of rejected drafts reveals persistent domain-agnostic challenges involving formatting, statement validity, and solution-step completeness. These findings demonstrate that VeriMath can bridge generative AI and dependable educational applications by producing highly reviewable assessment drafts within tightly constrained national curriculum frameworks.

Figures & tables

Explore similar work

CardsList
  1. ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality Assessment

    Sep 14, 2026Junkai Tong, Mingjia Li, Haoran Chen +4Educational AssessmentAutomated Evaluation

  2. Generative AI performance in core undergraduate mathematics: a curriculum-level case study

    Sep 15, 2025Benjamin J. Walker, Nikoleta Kalaydzhieva, Beatriz Navarro Lameda +1Educational AssessmentGenerative AI in Education

  3. TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Generation from Science Curriculum Materials

    Aug 13, 2026Fatema Tuj Johora Faria, Mukaffi Bin Moin, M. F. Mridha +1Automated Test GenerationEducational Assessment