figma

Existing UI prototyping tools provide weak support for integrating design artifacts such as screenshots and sketches, hindering component reuse, semantic integration, and cross-role collaboration. This paper proposes a novel UI prototyping paradigm grounded in Conceptual Blending Theory, the first to concretize cognitive-science-based blending mechanisms into an interactive tool. It enables semantic-level element mixing across heterogeneous design examples through example-driven component extraction and semantic alignment, lightweight vision–semantics mapping, and real-time blended preview—facilitating staged intent articulation by developers. An empirical study with 14 frontend developers demonstrates that the approach significantly reduces prototype initiation time (average improvement of 42%), stimulates highly unexpected creative combinations (68% novel composition rate), and enhances design–development collaboration efficiency.

Existing vision-language models (VLMs) lack systematic evaluation benchmarks for tool-driven UI design tasks—such as those performed in Figma or Sketch—hindering progress in professional design automation. Method: We introduce CANVAS, the first benchmark tailored for tool-augmented VLMs in UI design, comprising 598 context-aware design tasks across 30 mobile UI scenarios. It explicitly distinguishes “design reproduction” and “design modification” tasks, built upon real-world UI data with human-annotated ground truth. Our methodology employs a context-aware VLM–tool API co-execution framework for precise tool invocation. Contribution/Results: Experiments demonstrate that state-of-the-art VLMs exhibit nascent capability in collaborative tool-based design; however, strategic tool selection and design quality remain critical bottlenecks. CANVAS provides a reproducible, empirically grounded evaluation framework to advance VLM interaction, iterative refinement, and integration within professional design software.

This work proposes an interactive UI design system that addresses the challenges non-expert users face in expressing design intent and trusting retrieved examples, which often lead to design fixation or disorientation. The system uniquely integrates multimodal retrieval-augmented generation (MMRAG) with source transparency, enabling fine-grained retrieval, remixing, and adaptation of UI examples at both interface and component levels. By transparently presenting metadata such as example ratings, download counts, and developer information, the system enhances users’ confidence in their design decisions. User studies demonstrate that this approach significantly improves users’ ability to achieve their design goals, facilitates efficient iteration, and encourages diverse exploration, effectively balancing controllability with creative discovery.

This paper addresses the challenge of operationalizing generative AI within collaborative software engineering teams. Drawing on a design study with 39 industry experts—including field observations, semi-structured interviews, and multi-role workshops—we systematically investigate how prompt engineering supports cross-functional AI prototyping and iterative co-design. Our study is the first to characterize three core phenomena in collaborative prompt prototyping: (1) the emergent construction of shared coordination norms, (2) dynamic role evolution across developers, domain experts, and AI specialists, and (3) context-sensitive evaluation mechanisms for prompt efficacy. We propose a generative-content-feature-driven rapid iteration paradigm and distill a reusable prompt prototyping strategy framework. Key technical challenges—including model opacity and example overfitting—are empirically identified. The findings provide both methodological grounding and actionable practice guidelines for industrial software teams, advancing the shift from generative AI as a technical capability to a collaborative design enabler.

To address the high learning barrier and non-intuitive interaction of EDA tools in analog circuit layout design, this paper proposes the first LLM-based multi-agent collaborative framework tailored for EDA analog design. The framework integrates natural language understanding with domain-specific EDA knowledge to enable end-to-end mapping from high-level design intent to executable scripts, while supporting context-aware interactive suggestions. It achieves tight integration with industrial EDA toolchains—particularly Cadence Virtuoso—to establish a closed-loop automated layout system. Experimental evaluation demonstrates over 70% reduction in user interaction steps and a 55% decrease in task completion time for novice designers, significantly improving both design efficiency and usability. The core contribution lies in pioneering an EDA-specialized LLM multi-agent collaboration paradigm, overcoming the limitations of conventional command-line and GUI-based interactions.

Existing generative UI (GenUI) tools rely on unstructured prompts, depth-first exploration strategies, and high-fidelity outputs, which hinder effective support for early-stage UI design exploration. This work proposes a contrastive GenUI approach that employs structured inputs, breadth-first exploration, and low-fidelity generation. Through controlled experiments—the first to systematically evaluate the impact of input structure, exploration strategy, and output fidelity on early design—we assess this paradigm using large language model–generated prototypes and user studies. Involving 24 UX designers and product managers, our findings indicate that structured inputs enhance visibility across design dimensions yet raise usability barriers; breadth-first exploration expands the creative solution space but introduces challenges in multi-screen preview management; and expert users still favor high-fidelity outputs. The study elucidates key trade-offs and contextual applicability among different GenUI paradigms.

Designers often struggle to effectively apply insights from human-computer interaction (HCI) research due to challenges in retrieval, disciplinary terminology barriers, and a lack of contextualized, actionable guidance. To address this gap, this work proposes ReFinE—the first Figma plugin that automatically synthesizes HCI research findings and integrates them directly into the UI design workflow. Leveraging natural language processing and context-aware recommendation techniques, ReFinE delivers real-time, visual, and actionable design suggestions tailored to the designer’s current task. Findings from a user study demonstrate that ReFinE significantly reduces cognitive load, enhances designers’ ability to incorporate empirical research evidence into their practice, improves design quality, and accelerates iterative prototyping cycles.

This work addresses the inefficiency and lack of guidance faced by front-end developers when manually selecting plausible and natural attribute values for instantiating reusable UI components within a vast design space. To tackle this challenge, the paper introduces the concept of “discriminative variants,” which uniquely integrates symbolic reasoning with large language models (LLMs). Symbolic reasoning identifies visually salient attributes, while the LLM leverages real-world knowledge to generate component instances that balance fidelity to exemplars with meaningful differentiation. This approach shifts the paradigm from ad hoc manual configuration to structured exploration of the design space. A user study (n=12) demonstrates that the generated variants effectively aid developers in comprehending the design space, significantly improving both instantiation efficiency and user experience, while maintaining strong domain relevance.

This study addresses the persistent challenges of version control in modern computer-aided design (CAD), where data complexity and strong interdependencies hinder effective implementation, thereby limiting design traceability, variant management, and team collaboration. Through qualitative content analysis, the authors systematically coded and synthesized insights from 170 online forum posts, revealing recurring sociotechnical challenges that CAD users face in version management, continuity, scoping, and distribution. The work introduces “infrastructural reflexivity” as a novel design principle for CAD tools, emphasizing support for coordinated work and cross-boundary collaboration. This concept offers actionable guidance for software developers and opens new research avenues for reimagining version control systems in complex design environments.

This study addresses the challenge in traditional fashion design of reconciling professional creative intent with users’ authentic preferences, which often results in low user engagement and inefficient preference elicitation. To bridge this gap, the authors propose a three-stage AI-augmented co-design system: designers first articulate an initial concept; users then express their preferences intuitively through an interactive interface; and an AI module interprets user interaction data, maps it to design semantics, and assists designers in synthesizing feedback into refined final designs. The system introduces a novel multi-platform collaborative framework that preserves expert design judgment while enabling non-expert users to convey preferences effectively, thereby achieving intelligent integration of user input and design decisions. User studies demonstrate that the approach significantly improves both the efficiency of preference collection and the accuracy of analysis, successfully balancing creative vision with user needs.