Reflexa: Uncovering How LLM-Supported Reflection Scaffolding Reshapes Creativity in Creative Coding

2026-01-25

AI Summary

This work proposes a large language model (LLM)-based reflective scaffolding framework to address the challenges creative coders face in effectively reflecting on their work due to ambiguous intent, unpredictable outputs, and code complexity—factors that often hinder deep exploration. Rather than treating the LLM as an isolated prompting tool, the system integrates it as a structured reflection mechanism that orchestrates human–AI interaction through dialogic guidance, visualized version navigation, and iterative suggestion pathways. Empirical evaluation demonstrates that this approach significantly enhances users’ sense of control over the creative process, broadens the scope of exploration, and improves both the originality and aesthetic quality of the resulting artifacts. The study thus introduces a novel interaction paradigm for human–AI co-creation grounded in systematic, scaffolded reflection.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Interaction Techniques and Devices
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Creative coding requires continuous translation between evolving concepts and computational artifacts, making reflection essential yet difficult to sustain. Creators often struggle to manage ambiguous intentions, emergent outputs, and complex code, limiting depth of exploration. This work examines how large language models (LLMs) can scaffold reflection not as isolated prompts, but as a system-level mechanism shaping creative regulation. From formative studies with eight expert creators, we derived reflection challenges and design principles that informed Reflexa, an integrated scaffold combining dialogic guidance, visualized version navigation, and iterative suggestion pathways. A within-subject study with 18 participants provides an exploratory mechanism validation, showing that structured reflection patterns mediate the link between AI interaction and creative outcomes. These reflection trajectories enhanced perceived controllability, broadened exploration, and improved originality and aesthetic quality. Our findings advance HCI understanding of reflection from LLM-assisted creative practices, and provide design strategies for building LLM-based creative tools that support richer human-AI co-creativity.

Problem

• creative coding
• reflection
• large language models
• creativity
• human-AI co-creativity

Innovation

• reflection scaffolding
• large language models
• creative coding
• human-AI co-creativity
• structured reflection