# Exploring the Potential of Metacognitive Support Agents for Human-AI Co-Creation

arXiv: https://arxiv.org/abs/2506.12879 · HTML: https://mlsanity.com/paper/2506.12879/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 123 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [A Review of Deep Learning Techniques for Speech Processing](https://mlsanity.com/paper/2305.00359/) (2023)
- [Automatic Generation of Socratic Subquestions for Teaching Math Word Problems](https://mlsanity.com/paper/2211.12835/) (2022)
- [An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era](https://mlsanity.com/paper/2210.03538/) (2022)
- [Exploring Challenges and Opportunities to Support Designers in Learning to Co-create with AI-based Manufacturing Design Tools](https://mlsanity.com/paper/2303.00192/) (2023)
- [Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems](https://mlsanity.com/paper/2304.09821/) (2023)
- ["It's like a rubber duck that talks back": Understanding Generative AI-Assisted Data Analysis Workflows through a Participatory Prompting Study](https://mlsanity.com/paper/2407.02903/) (2024)
- [SimuLearn: Fast and Accurate Simulator to Support Morphing Materials Design and Workflows](https://mlsanity.com/paper/2007.15065/) (2020)
- [Using Think-Aloud Data to Understand Relations between Self-Regulation Cycle Characteristics and Student Performance in Intelligent Tutoring Systems](https://mlsanity.com/paper/2312.05675/) (2023)
- [Robot Duck Debugging: Can Attentive Listening Improve Problem Solving?](https://mlsanity.com/paper/2301.06511/) (2023)

## Built on by (most cited first, 6 of 6)

- [Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design](https://mlsanity.com/paper/2603.24768/) (2026)
- [Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz](https://mlsanity.com/paper/2510.06872/) (2025)
- [Vidmento: Creating Video Stories Through Context-Aware Expansion With Generative Video](https://mlsanity.com/paper/2601.22013/) (2026)
- [MetaCues: Enabling Critical Engagement with Generative AI for Information Seeking and Sensemaking](https://mlsanity.com/paper/2603.19634/) (2026)
- [Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts](https://mlsanity.com/paper/2606.27233/) (2026)
- [Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants](https://mlsanity.com/paper/2609.20143/) (2026)

## Abstract (arXiv)

Despite the potential of generative AI (GenAI) design tools to enhance design processes, professionals often struggle to integrate AI into their workflows. Fundamental cognitive challenges include the need to specify all design criteria as distinct parameters upfront (intent formulation) and designers' reduced cognitive involvement in the design process due to cognitive offloading, which can lead to insufficient problem exploration, underspecification, and limited ability to evaluate outcomes. Motivated by these challenges, we envision novel metacognitive support agents that assist designers in working more reflectively with GenAI. To explore this vision, we conducted exploratory prototyping through a Wizard of Oz elicitation study with 20 mechanical designers probing multiple metacognitive support strategies. We found that agent-supported users created more feasible designs than non-supported users, with differing impacts between support strategies. Based on these findings, we discuss opportunities and tradeoffs of metacognitive support agents and considerations for future AI-based design tools.