Beyond AI Delegation: A Prompt Pattern Framework for Productive Struggle and Evaluative Judgement in Secure Coding Education

• URL: http://arxiv.org/abs/2605.24447v1
• Date: Sat, 23 May 2026 07:35:49 GMT
• Title: Beyond AI Delegation: A Prompt Pattern Framework for Productive Struggle and Evaluative Judgement in Secure Coding Education
• Abstract summary: Large language models make it easy for students to delegate writing, analysis, and problem-solving to automated systems.<n>We introduce a practical framework that helps educators keep GenAI in the course without removing the cognitive demands that make it worthwhile.
• Score: 0.45706494756895794
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models make it easy for students to delegate writing, analysis, and problem-solving to automated systems, bypassing the effortful engagement that produces lasting understanding. We introduce a practical framework that helps educators keep GenAI in the course without removing the cognitive demands that make it worthwhile. We apply Design Science Research (DSR) to synthesise and adapt a taxonomy of nine prompt engineering patterns from established catalogs in the computer science literature, mapped to two pedagogical constructs: Productive Struggle and Evaluative Judgement. A course design for an Advanced Secure Coding module, structured using the DELTA framework, demonstrates the artifact's applicability. Nine prompt patterns, each mapped to a specific pedagogical function, give instructors fine-grained control over how students interact with AI. The secure coding design shows how three patterns (Flipped Interaction, Alternative Approaches, and Cognitive Verifier) scaffold vulnerability discovery and remediation while keeping students in the reasoning role. The framework provides a replicable approach to designing AI-augmented learning experiences that preserve student reasoning, and establishes a structured basis for future empirical evaluation in live course settings.

Related papers

• Structuring Transparency: Developing Domain-Specific Generative AI Declaration Frameworks in Higher Education [1.217503190366097]
  This paper contributes a design artefact and an accompanying position, developed for a Computer Science department on the basis of an existing taxonomy of GenAI usage.<n>By categorising AI usage across specific cognitive and developmental stages, the framework encourages students to reflect on their own learning process.
  arXiv  Detail & Related papers  (2026-06-11T14:18:34Z)
• Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues [46.915280360954576]
  We propose an interpretable difficulty-aware conversational KT framework built upon large language models (LLMs)<n>The framework incorporates the original textual question and the next tutor-posed task to estimate the student's knowledge state and the difficulty of the upcoming turn.<n>We evaluate the framework on two tutor-student dialogue datasets.
  arXiv  Detail & Related papers  (2026-05-01T21:07:24Z)
• Knowledge Markers: An AI-Agnostic Concept for the Design of Programming Courses [0.0]
  This paper contributes knowledge markers as a lightweight, AI-agnostic, course-level operationalisation for course design.<n>We show how the labels can be embedded at fine granularity in open teaching artifacts.<n>We demonstrate the approach by analysing, redesigning, and descriptively evaluating an introductory programming course.
  arXiv  Detail & Related papers  (2026-04-07T18:13:40Z)
• Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking [154.2388970262703]
  Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework.<n>We introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm that alternates between analytic and drafting operations.<n>By interleaving textual thoughts with visual thoughts, AD-Loop enables models to iteratively refine both comprehension and outputs, fostering genuine synergy.
  arXiv  Detail & Related papers  (2026-02-24T23:26:09Z)
• The Vibe-Check Protocol: Quantifying Cognitive Offloading in AI Programming [5.584060970507507]
  Vibe Coding'' is a paradigm where developers articulate high-level intent through natural language and delegate implementation to AI agents.<n>This paper proposes a theoretical framework to investigate the research question: textitIs Vibe Coding a better way to learn software engineering?
  arXiv  Detail & Related papers  (2026-01-02T06:13:41Z)
• From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Education [0.6372261626436676]
  Generative AI enables personalized computer science education at scale, yet questions remain about whether such personalization supports or undermines learning.<n>This scoping review synthesizes 32 studies purposively sampled from 259 records to map personalization mechanisms and effectiveness signals.<n>We identify five application domains: intelligent tutoring, personalized materials, formative feedback, AI-augmented assessment, and code review, and analyze how design choices shape learning outcomes.
  arXiv  Detail & Related papers  (2025-12-23T19:20:34Z)
• SocraticAI: Transforming LLMs into Guided CS Tutors Through Scaffolded Interaction [0.0]
  We present SocraticAI, a scaffolded AI tutoring system that integrates large language models (LLMs) into undergraduate Computer Science education.<n>The system enforces well-formulated questions, reflective engagement, and daily usage limits while providing Socratic dialogue scaffolds.<n>Initial deployment demonstrates that students progress from vague help-seeking to sophisticated problem decomposition within 2-3 weeks.
  arXiv  Detail & Related papers  (2025-12-03T06:49:32Z)
• Designing LMS and Instructional Strategies for Integrating Generative-Conversational AI [0.0]
  This study introduces a structured framework for designing an AI-powered Learning Management System.<n>It integrates generative and conversational AI to support adaptive, interactive, and learner-centered instruction.
  arXiv  Detail & Related papers  (2025-08-31T06:01:50Z)
• KERAIA: An Adaptive and Explainable Framework for Dynamic Knowledge Representation and Reasoning [46.85451489222176]
  KERAIA is a novel framework and software platform for symbolic knowledge engineering.<n>It addresses the persistent challenges of representing, reasoning with, and executing knowledge in dynamic, complex, and context-sensitive environments.
  arXiv  Detail & Related papers  (2025-05-07T10:56:05Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control [44.77500987121531]
  Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations. We develop a novel HIL algorithm based on Adversarial Inverse Reinforcement Learning. We also propose a Variational Autoencoder framework for learning with our objectives in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-10-05T00:28:26Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.