# Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding

arXiv: https://arxiv.org/abs/2402.09750 · HTML: https://mlsanity.com/paper/2402.09750/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 49 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 13 of 13)

- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development](https://mlsanity.com/paper/2302.07080/) (2023)
- [CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs](https://mlsanity.com/paper/2401.11314/) (2024)
- [NatGen: Generative pre-training by "Naturalizing" source code](https://mlsanity.com/paper/2206.07585/) (2022)
- [Spellburst: A Node-based Interface for Exploratory Creative Coding with Natural Language Prompts](https://mlsanity.com/paper/2308.03921/) (2023)
- [Promptly: Using Prompt Problems to Teach Learners How to Effectively Utilize AI Code Generators](https://mlsanity.com/paper/2307.16364/) (2023)
- [An Aligned Rank Transform Procedure for Multifactor Contrast Tests](https://mlsanity.com/paper/2102.11824/) (2021)
- [A Study of Editor Features in a Creative Coding Classroom](https://mlsanity.com/paper/2301.13302/) (2023)
- [InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs](https://mlsanity.com/paper/2312.09672/) (2023)

## Built on by (most cited first, 3 of 3)

- [DesignerlyLoop: Forming Design Intent through Curated Reasoning for Human-LLM Alignment](https://mlsanity.com/paper/2511.15331/) (2025)
- [MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks](https://mlsanity.com/paper/2604.23788/) (2026)
- [AI as Friction for Reflection Support in Ideation](https://mlsanity.com/paper/2607.26827/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly integrated into creative coding, yet how users reflect, and how different co-creation conditions influence reflective behavior, remains underexplored. This study investigates situated, moment-to-moment reflection in creative coding under two prompting strategies: the entire task invocation (T1) and decomposed subtask invocation (T2), to examine their effects on reflective behavior. Our mixed-method results reveal three distinct reflection types and show that T2 encourages more frequent, strategic, and generative reflection, fostering diagnostic reasoning and goal redefinition. These findings offer insights into how LLM-based tools foster deeper creative engagement through structured, behaviorally grounded reflection support.