Creativity from Friction: Human-AI Interaction for Exploratory Structural Design

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Ricardo Maia Avelino, Rita Sevastjanova, Tom Van Mele, Philippe Block, Mennatallah El-Assady
• Venue: arXiv: cs.HC
• Published: 2026-07-08
• Collected: 2026-07-09
• URL: http://arxiv.org/abs/2607.07521v1
• PDF: https://arxiv.org/pdf/2607.07521v1
• DOI: UNKNOWN

Plain-Language Brief

This research discusses the limitations of AI agents in creative fields, focusing on structural design and architecture. The paper proposes that interactive systems that help users explore alternatives and refine partial solutions are needed, as they can stimulate novel and creative solutions due to the constraints in the design process. The authors present principles for a pilot design interface based on these ideas, which aim to reduce repetitive modeling friction while preserving reflective design friction.

What the Document Says

• AI agents in creative fields often fail to meet users' needs.
• Interactive systems are needed for exploratory structural design and architecture.
• These interactive systems should help users externalize, develop ideas, explore alternatives, and refine partial solutions.
• The final product of such designs should comply with spatial configuration, mechanical behavior, material quantities, and costs constraints.
• Friction in the design process can stimulate novel and creative solutions.
• Current generative AI goals aim to remove friction and provide final solutions.
• Creators, such as structural designers, develop ideas through iterative work.
• The paper presents principles for a pilot design interface based on conversational, multimodal, and responsive vision-language models that follow and augment the discipline's creative process.
• The study involved experts in the field and shows how structural designers perceive interactive AI systems.

Key Concepts Mentioned

• AI
• creativity
• friction
• structural design
• interactive systems

Claims Made by the Document

• Interactive systems can stimulate novel and creative solutions in structural design.
• Current generative AI goals are misaligned with the needs of creators.

Evidence Used

• The paper discusses the benefits of interactive systems for stimulating creative solutions.
• The authors argue that current AI goals do not meet the needs of creative fields.

Methods / Approach

• Presentation of principles for a pilot design interface.
• Study with experts in the field.

Limitations Stated by the Authors

The paper presents a pilot design interface and studies it with experts in the field, but it does not provide extensive testing or real-world applications.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The agent's understanding of the specifics of structural design and architecture is limited to the information provided in the text.

Open Questions

• What are the long-term implications of using interactive AI systems for creative work?
• How can the performance of these systems be optimized for different creative fields?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper does not discuss the long-term implications or optimization of the presented system.

Raw Abstract / Excerpt

AI agents that generate final answers based on user input often do not meet the needs of creative fields. Fields such as structural design and architecture need interactive systems that help users externalise and develop ideas, explore alternatives, and refine partial solutions. The final product of such designs needs to comply with many constraints concerning, e.g., spatial configuration, mechanical behaviour, material quantities, and costs. These constraints create friction in the design process, which can stimulate novel and creative solutions. In this paper, we discuss the misalignment between current generative AI goals to remove friction and provide final solutions and the needs of creators, such as structural designers, who develop ideas through iterative work. We present the design dimensions of systems allowing for constrained human-AI co-creation that rely on vision-language models making structural exploration conversational, multimodal, and responsive to evolving human intent in ways that follow and augment the discipline's creative process. Through a pilot design interface based on these principles and a study with experts in the field, this paper shows how structural designers perceive interactive AI systems and how such systems can support design space exploration by reducing repetitive modelling friction while preserving reflective design friction.