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 current AI systems in creative fields like architecture and structural design, which often require exploratory and iterative processes. The authors propose a new approach for human-AI interaction that focuses on conversational, multimodal, and responsive systems to help designers externalize, develop, and explore ideas within the constraints of spatial configuration, mechanical behavior, material quantities, and costs.

What the Document Says

• AI agents often fail to meet needs in creative fields like structural design and architecture.
• Current AI aims to remove friction and provide final solutions, but creators develop ideas iteratively.
• The paper discusses the misalignment between AI's goals and the needs of creators.
• A new approach for human-AI interaction is proposed for structured exploration and design co-creation.
• The approach emphasizes conversational, multimodal, and responsive systems following creative processes.
• A pilot design interface based on these principles was tested with experts in the field.

Key Concepts Mentioned

• AI
• creative fields
• structural design
• architecture
• human-AI interaction
• constrained co-creation
• vision-language models

Claims Made by the Document

• Current AI systems do not meet the needs of creative fields.
• Creators develop ideas iteratively.
• There is a misalignment between current AI goals and the needs of creators.

Evidence Used

• Discussion of challenges faced by creators in using current AI systems.

Methods / Approach

• Proposal of a new approach for human-AI interaction.
• Development and testing of a pilot design interface.

Limitations Stated by the Authors

The study only involved experts in the field, which may limit the generalizability of findings.

Limitations Noted by the Agent

Agent interpretation — not from the source.

This summary assumes that the text accurately represents the authors' research and intentions. However, interpretation can vary based on context and individual perspectives.

Open Questions

• What are specific examples of the misalignment between current AI goals and the needs of creators?
• How does the proposed human-AI interaction approach address these misalignments in practice?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The text focuses on discussing problems and proposals, but it lacks concrete examples or detailed descriptions of how the new approach works.

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.