Indirect and Direct AI Scaffolding for Computational Problem Posing: A Pilot Experience Report

Jul 16, 2026

Upload by Ophelia

Problem posing strengthens computing education by having learners construct, refine, and reflect on problems instead of only solving them. The experience report describes the design and pilot deployment of two LLM-powered scaffolding systems across two computational scenarios with different openness. Both evaluated student-generated problems using Bloom’s Taxonomy criteria with a shared assessment framework, differing only in output modality: Indirect scaffolding used guiding questions; Direct scaffolding provided worked examples. A counterbalanced within-subjects pilot with 20 graduate students gathered quality ratings, surveys, and interviews, showing complementary benefits.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

Abstract

Introduction

Problem posing and learning challenges

Role of LLMs in scaffolding

Design tension: support vs. offloading

Indirect and Direct AI Scaffolding for Computational Problem Posing: A Pilot Experience Report Shayla Sharmin [shayla@udel.edu](shayla@udel.edu)[ ](shayla@udel.edu)University of Delaware Newark, Delaware, USA Mohammad Al-Ratrout [mratrout@udel.edu](mratrout@udel.edu)[ ](mratrout@udel.edu)University of Delaware Newark, Delaware, USA Mohammad Fahim Abrar [fahim@udel.edu](fahim@udel.edu)[ ](fahim@udel.edu)University of Delaware Newark, Delaware, USA Roghayeh Leila Barmaki [rlb@udel.edu](rlb@udel.edu)[ ](rlb@udel.edu)University of Delaware Newark, Delaware, USA arXiv :2607 .09628v1 [ cs .HC] 10 Jul 2026 Figure 1: Overview of the two LLM scaffolding systems. Both used the same Bloom’s Taxonomy rubric but differed in output modality: Indirect asked guiding questions, whereas Direct provided worked examples. Both improved problem quality. Abstract Problem posing is a valuable learning activity in computing education, encouraging learners to actively construct, refine, and reflect on problems rather than simply solving them. This experience report presents the design and pilot deployment of two LLM-powered scaffolding systems for supporting problem posing across two computational scenarios with different levels of task openness. Both systems assessed student-generated problems using Bloom’s Taxonomy-based criteria and applied the same assessment framework, differing only in output modality: one provided guiding questions (Indirect scaffolding), while the other offered worked examples (Direct scaffolding) . We conducted a within-subjects, counterbalanced pilot study with 20 graduate students and collected problem-quality ratings, user-experience surveys, and post-session interviews. Our deployment showed that both systems supported Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org). SIGCSE TS, Sacramento, CA © 2027 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2027/02 [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX) problem refinement in complementary ways, each offering distinct benefits. Direct scaffolding produced greater immediate improvements, while interviews showed that participants valued Indirect scaffolding for promoting deeper reflection on their own problem design. Based on these findings, we suggest sequencing the two modalities by beginning with Indirect scaffolding to promote reflection, then shifting to Direct scaffolding when learners become stuck. These lessons offer an initial practical strategy for integrating LLM-based scaffolding into computing classrooms. CCS Concepts • Applied computing → Interactive learning environments; Computer-assisted instruction; • Human-centered computing → User studies. Keywords Large Language Models (LLMs), problem posing, computing education, LLM scaffolding, indirect scaffolding, direct scaffolding ACM Reference Format: ShaylaSharmin, Mohammad Fahim Abrar, Mohammad Al-Ratrout, andRoghayeh Leila Barmaki. 2027. Indirect and Direct AI Scaffolding for Computational Problem Posing: A Pilot Experience Report. In Proceedings of Make sure to enter the correct conference title from your rights confirmation email (SIGCSE TS) . ACM, New York, NY, USA, 7 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX) 1 Introduction Problem posing is an instructional approach w

FAQs

What problem does the report address in computational problem posing?

Students often lack actionable feedback to improve the problems they pose, and instructors face difficulty providing timely, individualized feedback in large classes.

How do the two proposed LLM scaffolding systems differ?

Indirect scaffolding supports learners with guiding questions, while Direct scaffolding provides worked examples; both use the same Bloom’s Taxonomy-based assessment framework.

What did the pilot study find about their effectiveness?

Both systems improved problem refinement in complementary ways: Direct scaffolding produced stronger immediate improvements, while interviews indicated that Indirect scaffolding helped learners reflect more deeply on their own design.

Jul 16, 2026

Upload by Ophelia