interaction design

HCI research suffers from numerous context-dependent, non-replicable empirical findings. To address this, we propose *Interaction Cycle Diffraction*—the first method to formalize and compare user interaction behavior across experimental conditions using *interactional properties* (e.g., feedback latency, action reversibility, or mode-switching cost) as fundamental analytical units, rather than interface morphology. This framework systematically enables identification, extraction, and validation of reproducible interactional properties across diverse prototypes, technologies, tasks, and user populations. Through iterative user studies and prototype refinement, we demonstrate its utility in continuously optimizing design workflows and accumulating reusable empirical knowledge. Our work establishes the first reproducibility framework for interactional properties in ubiquitous UIs, offering a novel paradigm for building a theoretical taxonomy and empirical foundation for an interaction science. (138 words)

This work addresses the lack of explicit modeling of abstraction mechanisms in existing interactive system design, which hinders actionable design guidance. Through a systematic review of 457 publications, the study proposes the first abstraction-centered design space for interactive systems, structured around six core dimensions. Leveraging this framework, it reconceptualizes the Gulf of Execution and Evaluation model to reveal the cognitive and design mechanisms by which users and systems bridge the abstraction gap. By explicitly integrating abstraction into the theoretical foundations of human–computer interaction, this research synthesizes prior work, establishes a coherent theoretical basis, and offers systematic practical guidance for designing and evaluating abstraction mechanisms in interactive systems, thereby charting new directions for future inquiry.

Current HCI research overemphasizes interface appearance while neglecting the observability and reproducibility of actual interaction processes. To address this, we propose an interaction-behavior-centered research paradigm, establishing a standardized observational framework spanning technologies, design approaches, and user tasks. Our method employs experiment-driven application prototyping and empirical observation to systematically extract, validate, and accumulate reproducible interaction characteristics. The contributions are threefold: (1) the first ontology-oriented observational framework for human–computer interaction, enabling multi-condition reproducibility and integrative analysis; (2) tight coupling of user task requirements with technological evolution to support dynamic extraction and validation of interaction attributes; and (3) a scalable methodology and empirical foundation for uncovering fundamental principles governing interactive behavior. This paradigm shifts focus from static interface artifacts to observable, measurable, and repeatable interaction phenomena—thereby advancing HCI as an evidence-based science.

Existing visualization research predominantly focuses on *how to use* interactive features, neglecting the critical question of *how to construct* them. Method: We propose the first three-layer decoupled interaction authoring task model—intent–technique–component—derived from empirical coding and abstraction of 592 interaction units across 47 real-world applications. Contribution/Results: This model provides descriptive, evaluative, and generative capabilities, enabling the first unified formalization of interaction authoring intent, technical implementation, and component instantiation. It yields a reusable, theory-grounded classification framework that supports critical evaluation of existing visualization tools and informs the design and validation of next-generation low-code interaction authoring systems.

This study addresses the absence of a systematic approach for selecting appropriate human-AI interaction interfaces based on user needs and task complexity. It proposes a three-dimensional classification framework grounded in workflow complexity, AI autonomy, and AI reasoning capability, developed and validated through co-design workshops and longitudinal qualitative user studies. The work establishes, for the first time, a mapping between task complexity and interface modalities, offering actionable guidance for designing context-aware, scalable AI interfaces that support seamless transitions between modalities and enable users to exercise progressive control. The framework also balances operational impact and safety risks in high-autonomy scenarios. By providing product teams with a shared conceptual language, this research enhances the ability to achieve an effective balance between human oversight and AI autonomy in collaborative settings.

This study addresses the current lack of a systematic understanding of user interaction mechanisms with large language model–driven computer-use agents and the key design factors influencing their user experience (UX). Through a two-stage approach, the authors construct and empirically validate a UX design space for such agents. First, they synthesize findings from a literature review and expert interviews to develop a taxonomy encompassing dimensions such as user prompting, explainability, and user control. Second, they conduct a Wizard-of-Oz experiment across normal, error, and high-risk scenarios to observe user behaviors, revealing interdependencies among design dimensions and the diversity of user needs. This work presents the first systematically formulated and empirically validated UX design framework for LLM-driven agents, offering developers a structured and actionable foundation for design decisions.

This study addresses the absence of a unified theoretical framework that integrates psychological mechanisms, task orientation, and human-centered design principles to explain how AI system design influences human behavior. To bridge this gap, the authors propose the Integrated Information Processing (IIP) model, grounded in cybernetics and action regulation theory, which conceptualizes human–AI interaction as coupled control loops and establishes a common information-processing language applicable to both agents. The model introduces three integrative quality metrics—input sufficiency, reference consistency, and output operability—to theoretically predict human-centered benchmarks such as transparency and controllability, while mapping interface design choices to anticipated user behaviors. This framework offers actionable guidance for designing human–AI collaboration across diverse scenarios, fostering interactions characterized by greater autonomy and synergy.

This work proposes a new paradigm for software design tailored to AI agents as primary users, addressing the limitations of traditional human-centric approaches. It formally defines the concept of an “agent interface” for the first time, centering on callable capabilities and emphasizing machine interpretability, composability, and invocation reliability. Guided by the interaction requirements of large language model–based agents, the study introduces a capability-oriented software architecture and corresponding interface specifications. By establishing a conceptual foundation and design framework for AI-native systems, this research advances software engineering beyond monolithic applications toward dynamic, composable ecosystems of interoperable capabilities.

This work addresses the scarcity of user customization in everyday productivity tools and the lack of flexible, natural language–based mechanisms for adapting system behavior. It proposes embedding generative AI–driven conversational customization into email systems, enabling users to iteratively reshape their inbox structure, interface, and workflows through natural language, thereby transforming static interfaces into malleable data layers. Through a user-centered design probe, the study reveals that users prefer adaptive modifications grounded in existing patterns over creating configurations from scratch. While such customization significantly enhances tool flexibility, it also introduces risks of misconfiguration, necessitating continuous oversight and iterative refinement mechanisms. The findings illuminate practical pathways and design implications for integrating conversational customization into routine productivity applications.