Directive, Metacognitive or a Blend of Both? A Comparison of AI-Generated Feedback Types on Student Engagement, Confidence, and Outcomes

• URL: http://arxiv.org/abs/2510.19685v1
• Date: Wed, 22 Oct 2025 15:31:21 GMT
• Title: Directive, Metacognitive or a Blend of Both? A Comparison of AI-Generated Feedback Types on Student Engagement, Confidence, and Outcomes
• Authors: Omar Alsaiari, Nilufar Baghaei, Jason M. Lodge, Omid Noroozi, Dragan Gašević, Marie Boden, Hassan Khosravi,
• Abstract summary: This study presents a semester-long randomised controlled trial with 329 students in an introductory design and programming course using an adaptive educational platform.<n>Participants were assigned to receive directive, metacognitive, or hybrid AI-generated feedback that blended elements of both directive and metacognitive feedback.<n>Results showed that revision behaviour differed across feedback conditions, with Hybrid prompting the most revisions compared to Directive and Metacognitive.
• Score: 1.8839714322633465
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Feedback is one of the most powerful influences on student learning, with extensive research examining how best to implement it in educational settings. Increasingly, feedback is being generated by artificial intelligence (AI), offering scalable and adaptive responses. Two widely studied approaches are directive feedback, which gives explicit explanations and reduces cognitive load to speed up learning, and metacognitive feedback which prompts learners to reflect, track their progress, and develop self-regulated learning (SRL) skills. While both approaches have clear theoretical advantages, their comparative effects on engagement, confidence, and quality of work remain underexplored. This study presents a semester-long randomised controlled trial with 329 students in an introductory design and programming course using an adaptive educational platform. Participants were assigned to receive directive, metacognitive, or hybrid AI-generated feedback that blended elements of both directive and metacognitive feedback. Results showed that revision behaviour differed across feedback conditions, with Hybrid prompting the most revisions compared to Directive and Metacognitive. Confidence ratings were uniformly high, and resource quality outcomes were comparable across conditions. These findings highlight the promise of AI in delivering feedback that balances clarity with reflection. Hybrid approaches, in particular, show potential to combine actionable guidance for immediate improvement with opportunities for self-reflection and metacognitive growth.

Related papers

• Adaptive Scaffolding for Cognitive Engagement in an Intelligent Tutoring System [13.249968490944243]
  The ICAP framework defines four cognitive engagement levels: Passive, Active, Constructive, and Interactive.<n>We develop and evaluate a system that adaptively scaffolds cognitive engagement by dynamically selecting worked examples in two different ICAP modes.
  arXiv  Detail & Related papers  (2026-02-07T01:51:46Z)
• LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback [4.225232488376583]
  This study introduces a real-time AI-facilitated multimodal feedback system that integrates structured textual explanations with dynamic multimedia resources.<n>In an online crowdsourcing experiment, we compared this system against fixed business-as-usual feedback by educators across three dimensions.<n>Results showed that AI multimodal feedback achieved learning gains equivalent to original educator feedback while significantly outperforming it on perceived clarity, specificity, conciseness, motivation, satisfaction, and reducing cognitive load.
  arXiv  Detail & Related papers  (2026-01-21T18:58:08Z)
• From Co-Design to Metacognitive Laziness: Evaluating Generative AI in Vocational Education [0.0]
  This study examines the development and deployment of a Generative AI proof-of-concept (POC) designed to support lecturers in a vocational education setting in Singapore.<n>The POC achieved its primary operational goals: lecturers reported streamlined, reduced cognitive load, and observed improved student confidence in navigating course content.<n>Despite enhanced teaching processes, performance data revealed no significant improvement in overall student assessment outcomes.<n>The study raises consequential design questions regarding how AI tools can be engineered to minimise dependency, metacognitive development, and calibrate support across varying ability levels.
  arXiv  Detail & Related papers  (2025-12-13T12:26:25Z)
• UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models [59.693733170193944]
  Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings.<n>Recent reinforcement learning approaches address this limitation but face two critical challenges.<n>We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges.
  arXiv  Detail & Related papers  (2025-11-12T01:27:02Z)
• Socratic Mind: Impact of a Novel GenAI-Powered Assessment Tool on Student Learning and Higher-Order Thinking [2.192176712066146]
  This study examines the impact of Socratic Mind, a Generative Artificial Intelligence (GenAI) powered formative assessment tool on learning outcomes.<n>Students who engaged with the GenAI tool experienced significant gains in their quiz scores compared to those who did not.<n>Our findings highlight the promise of AI-mediated dialogue in fostering deeper engagement and higher-order cognitive skills.
  arXiv  Detail & Related papers  (2025-09-18T03:08:24Z)
• AI-Educational Development Loop (AI-EDL): A Conceptual Framework to Bridge AI Capabilities with Classical Educational Theories [8.500617875591633]
  This study introduces the AI-Educational Development Loop (AI-EDL), a theory-driven framework that integrates classical learning theories with human-in-the-loop artificial intelligence (AI)<n>The framework emphasizes transparency, self-regulated learning, and pedagogical oversight.
  arXiv  Detail & Related papers  (2025-08-01T15:44:19Z)
• When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration [79.69935257008467]
  We introduce Knowledge Integration and Transfer Evaluation (KITE), a conceptual and experimental framework for Human-AI knowledge transfer capabilities.<n>We conduct the first large-scale human study (N=118) explicitly designed to measure it.<n>In our two-phase setup, humans first ideate with an AI on problem-solving strategies, then independently implement solutions, isolating model explanations' influence on human understanding.
  arXiv  Detail & Related papers  (2025-06-05T20:48:16Z)
• Dynamic Programming Techniques for Enhancing Cognitive Representation in Knowledge Tracing [125.75923987618977]
  We propose the Cognitive Representation Dynamic Programming based Knowledge Tracing (CRDP-KT) model.<n>It is a dynamic programming algorithm to optimize cognitive representations based on the difficulty of the questions and the performance intervals between them.<n>It provides more accurate and systematic input features for subsequent model training, thereby minimizing distortion in the simulation of cognitive states.
  arXiv  Detail & Related papers  (2025-06-03T14:44:48Z)
• AI instructional agent improves student's perceived learner control and learning outcome: empirical evidence from a randomized controlled trial [29.45751702212421]
  This study examines the impact of an AI instructional agent on students' perceived learner control and academic performance in a medium demanding course with lecturing as the main teaching strategy.<n>Students in the AI instructional agent group reported significantly higher levels of perceived learner control compared to the other groups.
  arXiv  Detail & Related papers  (2025-05-28T16:13:27Z)
• Evaluating Trust in AI, Human, and Co-produced Feedback Among Undergraduate Students [2.935250567679577]
  This study compares undergraduate students' trust in large language models (LLMs), human, and human-AI co-produced feedback in their authentic HE context.<n>Findings revealed students preferred AI and co-produced feedback over human feedback regarding perceived usefulness and objectivity.<n>Educational AI experience improved students' ability to identify LLM-generated feedback and increased their trust in all types of feedback.
  arXiv  Detail & Related papers  (2025-04-15T08:06:36Z)
• Improving Question Embeddings with Cognitive Representation Optimization for Knowledge Tracing [77.14348157016518]
  Research on KT modeling focuses on predicting future student performance based on existing, unupdated records of student learning interactions.<n>We propose a knowledge-tracking cognitive representation optimization (CRO-KT) model that uses dynamic programming algorithms to optimize the structure of cognitive representation.
  arXiv  Detail & Related papers  (2025-04-05T09:32:03Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework [51.237191651923666]
  We investigate the potential of agent learning from trainers' facial expressions via interpreting them as evaluative feedback. With designed CNN-RNN model, our analysis shows that telling trainers to use facial expressions and competition can improve the accuracies for estimating positive and negative feedback. Our results with a simulation experiment show that learning solely from predicted feedback based on facial expressions is possible.
  arXiv  Detail & Related papers  (2020-01-23T17:50:57Z)

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.