CHI

This workshop applies human centered themes to a new and powerful technology, generative artificial intelligence (AI), and - among other approaches - particularly to Large Language Models (LLMs) and Foundation Models (FMs). Unlike AI systems that produce decisions or descriptions, generative AI systems can produce new and creative content that can include images, texts, music, video, code, and other forms of design. The results are often similar to results produced by humans. However, it is not yet clear how humans make sense of generative AI algorithms or their outcomes. It is also not yet clear how humans can control and more generally, interact with, these powerful capabilities in ethical ways. Finally, it is not clear what kinds of collaboration patterns will emerge when creative humans and creative technologies work together. Following successful workshops in 2022–2024, we convene the interdisciplinary research domain of generative AI and HCI. Participation is open to seasoned scholars and early career researchers. We solicit descriptions of completed projects, works-in-progress, and provocations. Together we will develop theories and practices in this intriguing new domain.

Participatory Design (PD) has become increasingly prevalent in Human-Computer Interaction (HCI) research. However, there remains a lack of comprehensive understanding of how PD has been used by HCI scholars. To bridge this gap, we sampled PD application cases (N = 185) from the SIGCHI conferences over the past decade and examined these cases through the dimensions of application features (e.g., contexts and functions of PD) and PD principles (e.g., its political commitment and mutual learning principle). Our analysis reveals the various ways PD has been applied in HCI and how its core features have been or have not been manifested in these cases. Based on these findings, we reflect on the conceptual understanding of PD within the HCI community and discuss potential misconceptions. Ultimately, we hope this work can serve as a useful reference for HCI researchers and beyond who are interested in incorporating PD into their design and research practices.

Communication in Human-Robot Interaction (HRI) often focuses on linguistic exchanges, with spoken dialogue providing a natural way for people to interact with robots. While direct verbal interaction can reduce barriers compared to other forms of interaction (e.g., text- or touch-based interfaces), it may also exclude users with speech, language, or cognitive differences, and they may not generalize well across cultures and contexts. Non-linguistic forms of communication, including non-verbal voice interactions and extra-linguistic signals (e.g., gesture, gaze, facial expressions, posture), offer complementary pathways that can enable more inclusive, accessible, and universal interactions. This workshop explores how non-linguistic communication can shape effective human-robot communication and collaboration. We aim to bring together researchers from HRI, conversational AI, linguistics, psychology, and accessibility studies to discuss opportunities, challenges, and design practices for integrating such features. The workshop seeks to advance inclusive design principles, bridge disciplines, and highlight future research directions on communication strategies that empower diverse users in their interactions with robots.

Good sleep hygiene is essential for quality sleep. This study investigates user preferences for the timing of interactions with features in smartwatch-based sleep hygiene games. Findings reveal that interactions during sleep are generally undesirable, with Sleep Health Points being the only exception. We also identified a misconception that games must involve active play, overlooking the potential of passive and idle game mechanics. Participants preferred engaging with planning and behavior-triggering features before the associated behavior, while reflection and reinforcement features, like reports and rewards, were favored post-behavior. The perceived dual functionality of certain features suggests that preferred interaction timing depends on users’ perceptions of the features’ roles. Users’ schedules and situational context, especially evening availability, also influenced their preferences. This study highlights the importance of aligning feature timing with user routines and perceptions, and advocates for game designs that blend active and passive elements to boost engagement and promote sleep hygiene.

This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR—always-available and seamlessly integrated into users’ daily environments—is becoming increasingly feasible. This workshop will explore how AI can drive such everyday AR experiences. We discuss a range of topics, including adaptive and context-aware AR, generative AR content creation, always-on AI assistants, AI-driven accessible design, and real-world-oriented AI agents. Our goal is to identify the opportunities and challenges in AI-enabled AR, focusing on creating novel AR experiences that seamlessly blend the digital and physical worlds. Through the workshop, we aim to foster collaboration, inspire future research, and build a community to advance the research field of AI-enhanced AR.

We are concurrently witnessing two significant shifts: voice and chat-based conversational user interfaces (CUIs) are becoming ubiquitous (especially more recently due to advances in generative AI and LLMs - large language models), and older people are becoming a very large demographic group (and increasingly adopting of mobile technology on which such interfaces are present). However, despite the recent increase in research activity, age-relevant and inter/cross-generational aspects continue to be underrepresented in both research and commercial product design. Therefore, the overarching aim of this workshop is to increase the momentum for research within the space of hands-free, mobile, and conversational interfaces that centers on age-relevant and inter- and cross-generational interaction. For this, we plan to create an interdisciplinary space that brings together researchers, designers, practitioners, and users, to discuss and share challenges, principles, and strategies for designing such interfaces across the life span. We thus welcome contributions of empirical studies, theories, design, and evaluation of hands-free, mobile, and conversational interfaces designed with aging in mind (e.g. older adults or inter/cross-generational). We particularly encourage contributions focused on leveraging recent advances in generative AI or LLMs. Through this, we aim to grow the community of CUI researchers across disciplinary boundaries (human-computer interaction, voice and language technologies, geronto-technologies, information studies, etc.) that are engaged in the shared goal of ensuring that the aging dimension is appropriately incorporated in mobile / conversational interaction design research.

This Birds-of-a-Feather (BoF) session offers LGBTQ+ researchers, educators, and practitioners in computing education an inclusive space for community-building, advocacy, and creative expression. The session seeks to expand beyond traditional networking by offering attendees a variety of opt-in activities, such as fiber arts, crafting, media sharing, and Pittsburgh-themed games. Attendees will have the opportunity to decompress after a long conference day, participate in discussions on queer scholarship and activism, and explore ways to make computing education more inclusive to LGBTQ+ individuals. A major focus of this session will be fostering connections beyond the conference itself. We will introduce a Slack channel for coordinating meetups throughout the conference and with monthly check-ins to ensure the community remains vibrant year-round. In light of the ongoing marginalization of the LGBTQ+ community and the political climate in the U.S., this session provides an essential space for decompressing, building support networks, and engaging in activism.

Recently, there is a growing trend of using generative AI systems and tools for fostering and protecting online collaborative communities. Yet, existing AI tools may introduce new risks and even harm to diverse communities’ online safety. How to better maximize the novel opportunities of AI and mitigate its emerging risks and harm for our future online safety is a critically needed discussion for the HCI community. Featuring experts from both industry and academia, the goal for this panel is to promote interdisciplinary, community-wide discussions and collective reflections on important questions and considerations at the unique intersection of AI and online communities, including but not limited to: how the design of AI systems may discourage existing online harm but also invite new online harm in various online spaces; how different populations, cultures, and communities may perceive and experience AI’s new roles for their online safety; and what new strategies, principles, and directions can be envisioned and identified to better design future AI technologies to protect rather than harm various online communities.

Exploratory search has been proposed as a model of search behaviour that is well suited to complex search scenarios. However, the simple interfaces that are commonplace across many search contexts limit the ability for searchers to undertake exploratory searches. Little support is provided for the discovery, learning, and investigation necessary for exploratory browsing, or the query (re)formulation, result examination, and information extraction required for focused searching. While the design and study of search interfaces that accommodate and support searchers in undertaking exploratory searches has increased in recent years, much of this work has been ad hoc in nature. In this perspective paper, five search interface design principles are presented that are specifically tuned to support exploratory search. An extension of the classical heuristic evaluation method is provided to support the inspection of prototype search interfaces with respect to the design principles. Recent research in the field is categorized according to these design principles. Patterns and gaps in the literature are identified, highlighting opportunities for further research on exploratory search interfaces. These principles provide a framework to guide the design and inspection of future search interfaces to support exploratory search, as well as a mechanism for comparing and contrasting the interactive information retrieval literature as it relates to supporting exploratory search through novel interface design.

Research on Cognitive Personal Informatics (CPI) is steadily growing as new wearable cognitive tracking technologies emerge on the consumer market, claiming to measure stress, focus, and other cognitive factors. At the same time, with generative AI offering new ways to analyse, visualize, and interpret cognitive data, we hypothesize that cognitive tracking will soon become as simple as measuring your heart rate during a run. Yet, cognitive data remains inherently more complex, context-dependent, and less well understood than physical activity data. This workshop brings together HCI experts to discuss critical questions, including: How can complex cognitive data be translated into meaningful metrics? How can AI support users’ data sensemaking without over-simplifying cognitive insights? How can we design inclusive CPI technologies that consider inter-personal variance and neurodiversity? We will map challenges and opportunities for CPI, considering recent AI advancements, and outline a research road map for the foreseeable future.

PDF inaccessibility is an ongoing challenge that hinders individuals with visual impairments from reading and navigating PDFs using screen readers. This paper presents a step-by-step process for both novice and experienced users to create accessible PDF documents, including an approach for creating alternative text for mathematical formulas without expert knowledge. In a study involving nineteen participants, we evaluated our prototype PAVE 2.0 by comparing it against Adobe Acrobat Pro, the existing standard for remediating PDFs. Our study shows that experienced users improved their tagging scores from 42.0% to 80.1%, and novice users from 39.2% to 75.2% with PAVE 2.0. Overall, fifteen participants stated that they would prefer to use PAVE 2.0 in the future, and all participants would recommend it for novice users. Our work demonstrates PAVE 2.0’s potential for increasing PDF accessibility for people with visual impairments and highlights remaining challenges.

Recent years have witnessed a growing interest in using robots to support Blind and Low Vision (BLV) people in various tasks and contexts. However, the Human-Computer Interaction (HCI) community still lacks a shared understanding of what, where, and how robots can benefit BLV users in their daily lives. In light of this, we conducted a systematic literature review to help researchers navigate the current landscape of this field through an HCI lens. We followed a systematic multi-stage approach and carefully selected a corpus of 76 papers from premier HCI venues. Our review provides a comprehensive overview of application areas, embodiments, and interaction techniques of the developed robotic systems. Further, we identified opportunities, challenges, and key considerations in this emerging field. Through this systematic review, we aim to inspire researchers, developers, designers, and HCI practitioners, to create a more inclusive environment for the BLV community.

Rapid advances in generative artificial intelligence suggest new possibilities for how human subjects research can be conducted in HCI studies. The panel invites both computer and social scientists to discuss future directions for applying simulated responses from large language models (LLM) for human subjects research. We discuss current challenges and opportunities in LLM simulations and brainstorm how insights across different disciplines might inform breakthroughs. We pay close attention to when and how applications of LLM simulations might augment human subjects research instead of steering it toward unintended directions. Discussions from the panel will provide preliminary ideas for when and how HCI researchers can apply LLM simulations to human subjects research pipelines. Through this engagement, we also aim to build a research community with shared interests.

… Furthermore, the organisers will encourage participation among IH conference attendees whose work intersects with topics such as digital health technologies, healthcare data systems, …

Interoception—the perception of internal bodily states such as heartbeat, hunger, and emotion—is foundational to well-being. Despite its significance in wellness technologies within Human-Computer Interaction (HCI), existing designs often impose a universalized model of bodily awareness, shaped by Western-centric assumptions, and overlook cultural variability. This paper integrates perspectives from neuroscience, cultural psychology, Science and Technology Studies (STS), and HCI to critically examine how culture shapes interoception. Through a thematic analysis of the literature, we identify key cultural and contextual dimensions that influence interoceptive experiences and their implications for wellness technologies. Rather than prescribing design solutions, this work challenges dominant paradigms in wellness technology, emphasizing interoception as culturally shaped rather than biologically universal. We highlight overlooked complexities in interoceptive experience and raise critical questions for the development of more inclusive, contextually responsive wellness technologies—technologies that do not simply monitor bodies, but support people in reconnecting with them on their own terms.

… the 2022 and 2024 Conference on Human Factors … CHI: Concretizing the material and epistemological practices of unmaking in HCI. In Extended Abstracts of the 2022 CHI Conference …

User engagement (UE) is widely discussed in HCI articles, but its definition, reliability, and application remain elusive. This research conducts a systematic literature review of 241 articles from 1993 to 2023 to analyze how UE is defined and measured within the domain of HCI. Our findings reveal significant definitional inconsistencies that hinder UE's practical application in HCI research and system design. Based on our findings, we recommend using UE as a categorical label rather than a unified construct until more systematic frameworks are established. We also highlight the need for divergent views of UE across HCI research communities as a valuable avenue to pursue. This divergent view approach can help HCI researchers focus on specific, measurable aspects of UE that align with specific community practices and norms. Our findings also suggest that until such a framework emerges, researchers should be aware of its limitations when using UE as a research construct.

… In this paper, we present findings from a corpus of scientific articles identified in the ACM … The most frequent venue in our corpus was CHI (the CHI Conference on Human Factors in …

This demo presents KimBilet.com, an educational platform that utilizes generative AI to create personalized educational content on demand. Catering to high-school and college students, instructors, job seekers, and lifelong learners, the system generates customized courses based on user prompts, covering any topic of interest. Each course may include a sequence of AI-created lessons and quizzes, providing detailed feedback for every quiz option to enhance understanding. The platform supports intuitive navigation through keyboard shortcuts and allows users to jump between course items seamlessly. It also maintains a history of completed quizzes to help users track their learning progress. Future enhancements include topic suggestions based on past interests, support for coding exercises, and multilingual support. This demo will showcase how KimBilet.com leverages AI to offer adaptive learning experiences, engage attendees through interactive exploration, and discuss its potential applications in educational settings. Participants will gain insights into integrating AI-driven tools into teaching and learning processes to address diverse educational needs.

… There is also increasing interest in self-directed VR training systems capable of teaching complex skills without human instructors [27]. This requires clear and reliable instructions …

The increasing capability of AI models to generate user interfaces has the potential to transform HCI and design practice. We invite researchers, designers, developers, and practitioners to explore how generative UI – interfaces created by AI models – will reshape design methods, workflows, and user experiences. Our goals are to (i) envision how generative UI can underpin innovative human-centric experiences, and (ii) reflect on how HCI and design practice could and should evolve to meet the opportunities and challenges this presents. This will be an interactive and discussion-oriented workshop, featuring a pop-up panel, creative ideation exercises, and collaborative artefact development. Artefacts produced through the workshop will be shared online afterwards and will, we hope, result in an Interactions or CACM article. We will welcome submissions from scholars and practitioners working on dynamic or generative UI, as well as those with expertise in related areas. To keep participation broad, participants will be asked to submit a two-page position paper (in ACM single column format), a two-page pictorial, or a two-minute video at the workshop website. We expect approximately 35 participants to register and attend, including the organizers.

The Wizard-of-Oz (WoZ) method has long been a core prototyping technique in Human-Computer Interaction (HCI), in which users interact with systems that seem autonomous but are actually controlled by hidden human operators. Advances in interactive technologies have expanded the landscape of future system behaviors, broadening both where and how WoZ is used. However, as more envisioned behaviors become technically feasible, the distinction between engineering a system and simulating an interaction becomes blurred, making it essential to clarify when and why to employ wizarding. This paper presents the first systematic review of WoZ in HCI, drawing on 194 papers from SIGCHI venues to identify ten application domains, five wizard control types, eight motivations, and five categories of concerns. Building on these findings, we propose a reciprocal evolution framework that interprets how technology and wizarding shape each other, and derive guidelines for the rigorous application of WoZ. We further illustrate the framework through emerging prototyping practices with Large Language Models (LLMs).

This meetup invites feminist researchers and allies to gather for a relaxed textile crafting session (for all levels of expertise, including complete beginners) alongside informal discussion of our research, experiences, and visions for community-building in HCI. Building on a tradition of grassroots feminist CHI gatherings named #CHIversity since 2017—including zine-making, lunch meetups, curating lists of feminist and social justice-oriented papers published at CHI each year, and online programs during the pandemic, this session provides a safe and creative space to connect in times of increasing academic precarity and censorship. The format facilitates networking across institutions, disciplines, and career stages, while fostering dialogue that affirms feminist ideas as central to HCI. By offering an explicitly critical feminist environment as part of the CHI program, this meetup not only supports immediate exchange and connection, but also strengthens the long-term continuity of feminist community within CHI.

The emergence of Large Language Model (LLM) agents enables us to build agent-based intelligent systems that move beyond the role of a “tool” to become genuine collaborators with humans, thereby realizing a novel human-agent collaboration paradigm. Our vision is that LLM agents should resemble remote human collaborators, which allows HCI researchers to ground the future exploration in decades of research on trust, awareness, and common ground in remote human collaboration, while also revealing the unique opportunities and challenges that emerge when one or more partners are AI agents. This workshop1 establishes a foundational research agenda for the new era by posing the question: How can the rich understanding of remote human collaboration inspire and inform the design and study of human-agent collaboration? We will bring together an interdisciplinary group from HCI, CSCW, and AI to explore this critical transition. The 180-minute workshop will be highly interactive, featuring a keynote speaker, a series of invited lightning talks, and an exploratory group design session where participants will storyboard novel paradigms of human-agent partnership. Our goal is to enlighten the research community by cultivating a shared vocabulary and producing a research agenda that charts the future of collaborative agents.

The interdisciplinary field of Human-Computer Interaction (HCI) thrives on productive engagement with different domains, yet this engagement often breaks due to idiosyncratic writing styles and unfamiliar concepts. Inspired by the dialogic model of abstract metaphors, as well as the potential of Large Language Models (LLMs) to produce on-demand support, we investigate the use of metaphors to facilitate engagement between Science and Technology Studies (STS) and System HCI. Our reflective-style survey with early-career HCI researchers (N=48) reported that limited prior exposure to STS research can hinder perceived openness of the work, and ultimately interest in reading. The survey also revealed that metaphors enhance likelihood to continue reading STS papers, and alternative perspectives can build critical thinking skills to mitigate potential risks of LLM-generated metaphors. We lastly offer a specified model of metaphor exchange (within this generative context) that incorporates alternative perspectives to construct shared understanding in interdisciplinary engagement.

Peer review determines which scholarship is legitimized; however, review biases often disadvantage scholarship that diverges from the norm. Human–Computer Interaction (HCI) lacks a systemic inquiry into how such biases affect underrepresented Global South (GS) scholarship. To address this critical gap, we conducted four focus groups with 16 HCI researchers studying the GS. Participants reported experiencing reviews that confined them to development research, dismissed their theoretical contributions, and questioned situated knowledge from GS communities. Both as authors and reviewers, participants reported experiencing the epistemic burden of over-explaining why knowledge from GS communities matters. Further, they noted being tokenized as “cultural experts” when assigned to review papers and pointed out that the hidden curriculum of writing HCI papers often gatekeeps GS scholarship. Using epistemic oppression as a lens, we discuss how review practices marginalize GS scholarship and outline actionable strategies for nurturing equitable epistemological evaluation of HCI scholarship.

Drawing on infrastructure studies in HCI and CSCW, this paper introduces Protocol Futuring, a methodological framework that extends design futuring by foregrounding protocols—rules, standards, and coordination mechanisms—as the primary material of speculative inquiry. Rather than imagining discrete future artifacts, Protocol Futuring examines how protocol rules accumulate drift, jam, and other second-order effects over long temporal horizons. We demonstrate the method through a case study of Knowledge Futurama, a multi-team participatory workshop exploring millennial-scale knowledge preservation. Using a relay format in which teams inherited and reinterpreted partially formed designs, the workshop revealed how ambiguous handovers, adversarial reinterpretations, shifting cultural norms, and crisis dynamics transform protocols as they move across communities and epochs. The case shows how Protocol Futuring makes infrastructural politics and long-run consequences analytically visible. We discuss the method’s strengths, limitations, and implications for researchers investigating emergent sociotechnical systems whose impacts unfold over extended timescales.

Human identity is fluid, relational, and context-dependent, yet many HCI practices—such as surveys, defaults, and personalization systems—rely on rigid categories that flatten lived experience and marginalize those who do not fit. Building on prior work in machine learning that critiques how datasets constrain identity, this workshop expands the conversation to HCI, exploring how categorical framings shape design, research, and everyday interactions in the context of technology. In this workshop, we aim to bring together HCI researchers, designers, and community partners to ask what it means to design for identities that are hybrid, shifting, and “in-between.” Through collaborative activities, participants will reflect on their own research practices and co-develop alternative framings of identity as contextual and evolving. To ground these discussions in lived experiences, we partner with Skin Mutts, an independent cultural platform that creates visual languages for expressing hybrid identities. The workshop outcomes will be translated into accessible formats, including a contribution to Skin Mutts Magazine, bringing the academic debate to a wider audience. By creating space for dialogue across disciplines and communities, this workshop invites the CHI community to imagine what HCI systems might look like if identity were treated not as a fixed label but as a dynamic and relational process.

Visions for the future of computing, such as those on Ubiquitous Computing or Tangible Interfaces, are highly cited and frequently used in teaching. Yet, we know little about the practical value of these visions for research on Human-Computer Interaction (HCI) or how HCI researchers engage with them individually and collectively. To address this gap, we conducted a survey with 172 HCI researchers. We identified key benefits and pitfalls as well as specific uses of visions by researchers. Researchers appreciate how visions guide us, drive us, and initiate new fields. Simultaneously, researchers acknowledge how visions create hype, restrict our creativity, and make us disregard real-world problems. Based on these insights, we derive tensions related to the pursuit of visions and discuss critical reading practices. Our paper offers a metascientific account of visions in the HCI field along with tools for critical reflection when engaging with them.

The latest advances in Artificial Intelligence (AI), such as Large Language Models (LLMs), have provoked a massive expansion and adoption of AI applications across the board, with seemingly no sector left untouched by recent developments. Anywhere we look, from healthcare to the creative industries, from education to entertainment, from sustainability to knowledge work, AI is being adopted and adapted, funded and fundraised for, developed and designed for, researched and used for doing research. As AI continues to be treated as a necessary and unquestioned solution for a range of societal problems, we seek to ponder and challenge its perceived suitability and inevitability. Moreover, we wonder how we can go about resisting AI solutionism (i.e., the idea that technology provides solutions to complex social problems) and who gets to resist it, in particular if the structures that surround people and their specific positions constrain them from doing so. This workshop will focus on gathering and sharing lessons from experiences resisting, or attempting to resist, AI solutionism; taking stock and revisiting previous learnings from decades of work within and beyond HCI; and envisioning ways, perspectives, tools, and practices to orient ourselves and each other towards more pluralistic futures.

AI has transformed methods and knowledge across many domains. However, the intersection of AI and haptics remains underexplored. While modern AI techniques – fueled by machine learning and using powerful techniques such as generative modeling and reinforcement learning – offer powerful opportunities for advancing haptic design, insights from haptics research, such as perception modeling and adaptive interaction - grounded in human touch, embodiment, and multisensory integration — can also play a critical role in shaping more human-centered AI systems. This workshop will bring together an interdisciplinary community of researchers from HCI, haptics, AI, robotics, and design to (1) identify pressing questions in haptics that could benefit from AI approaches and (2) highlight ways in which haptic knowledge can support the development of embodied and context-aware AI. Through position papers and paper presentations, we will map key challenges, exchange methods, and explore new research directions that connect the two fields. By framing haptics and AI as mutually reinforcing, the workshop aims to build a shared research agenda and foster collaborations that advance both the science of touch and the design of intelligent interactive systems.

Money and financial activities reflect social connections and societal norms. Collaborative financial activities and decision-making are highly common in our day-to-day activities. However, existing financial technologies (fintech) are often limited to individual-centric approaches and goals. Recent HCI work has repeatedly noted the need for creating new interaction strategies and design paradigms to better support our financial behaviors, habits, and goals. However, there has not been much concrete work yet, specifically when it comes to supporting collaborative behaviors and social norms that underpin much of our daily financial activities. In this in-person workshop, we will bring together an interdisciplinary group of researchers interested in reshaping the current landscape of digital money and fintech with a focus on social and collaborative interactions. Specifically, we will identify limitations of existing fintech approaches and potential strategies to address these limitations. We will also discuss key challenges for fintech design and development, including collaboration, privacy, agency, trust, and accessibility. The workshop will lead to identifying novel HCI research and implementation directions focusing on the future of financial technologies.

Given the growing global crises caused by the growth economy, there is a pedagogical responsibility to prepare future Human–Computer Interaction (HCI) professionals to embrace uncertainty and question unsustainable ideologies and practices. This workshop creates a space for educators and students to critically reflect on how HCI pedagogy might move beyond “bigger–and-faster” framings and toward practices of sufficiency, repair, and care. Through activities such as co-designing a living syllabus and reimagining evaluation criteria for student work, participants will explore how education can itself function as an infrastructural practice for cultivating post-growth perspectives within HCI. In doing so, this workshop aims to foreground pedagogy as a vital site where post-growth commitments can take root, reorienting the content and practice of HCI toward cultivating socio-ecologically just futures.

Governments are the primary providers of essential public services and are responsible for delivering them effectively. In high-stakes decision-making domains such as child welfare (CW), agencies must protect children without unnecessarily prolonging a family’s engagement with the system. With growing optimism around AI, governments are pushing for its integration but concerns regarding feasibility and harms remain. Through collaborations with a large Canadian CW agency, we examined how LocalLLM and BERTopic models can track CW case progress. We demonstrate how the tools can potentially assist workers in opportunistically addressing gaps in their work by signaling case progress/deviations. And yet, we also show how they fail to detect case trajectories that require discretionary judgments grounded in social work training, areas where practitioners would actually want support to pre-emptively address substantive case concerns. We also provide a roadmap of future participatory directions to co-design language tools for/with the public sector.

Natural interactions, such as those based on gesture input, feel intuitive, familiar, and well-suited to user abilities in context, and have been supported by extensive research. Contrary to the conventional mainstream, we advocate for non-natural interaction design as a transformative process that results in highly effective interactions by deliberately deviating from user intuition and expectations of physical-world naturalness or the context in which innate human modalities, such as gestures used for interaction and communication, are applied—departing from the established notion of the “natural,” yet prioritizing usability. To this end, we offer four perspectives on the relationship between natural and non-natural design, and explore three prototypes addressing gesture-based interactions with digital content in the physical environment, on the user’s body, and through digital devices, to challenge assumptions in natural design. Lastly, we provide a formalization of non-natural interaction, along with design principles to guide future developments.

… system that leverages conversational AI and body tracking to engage users with digital reproductions of artworks, advancing both interaction design and educational potential. …

Desktop Virtual Worlds (DVWs) offer unique spatial affordances for education, yet understanding of how these environments support meaningful learning experiences remains limited. This study introduces the Socio-Spatial Embodiment Model, a novel framework conceptualizing learning in DVWs as shaped by the interconnection of embodied presence, place-making, and community formation. Through semi-structured interviews conducted with 14 experienced educators from the Virtual Worlds Education Consortium, we investigated how these dimensions intersect and what design strategies facilitate this integration. Thematic analysis revealed that strategic design employs cognitive offloading techniques and biophilic metaphors to enhance embodied presence, balance familiar elements with spatial innovations to create meaningful places, and leverage synchronous engagement with institutional identity markers to facilitate learning communities. Our findings identified design strategies that facilitate stronger perceived student connections to the learning environment and community, when DVW designs address spatial, emotional, social, and cultural factors while reinforcing both cognitive and perceptual processes. This research advances understanding of embodied learning in virtual environments by identifying the dynamic interdependence among presence, place, and community, providing practical strategies for educators in creating more meaningful virtual learning experiences.

This study aims to develop and evaluate an interactive learning system for children. Through mixed-method research, combined with quantitative and qualitative data analysis, this study provides a comprehensive evaluation of the educational effectiveness of the system. The study involves children in grades 1–6, and data on learning effectiveness before and after using the system are collected through pre-experiments and formal experiments. The results of the quantitative analysis show that after using the system, the average improvement rates for students in grades 1–3 and 4–6 are 24.6% and 22.2% in mathematics and 28.1% and 26.8% in science. The average response time of the system is 1.77 s, with the longest response time being 3.1 s. User satisfaction reaches 94%, and the error rate is 0.2%. These results demonstrate that the developed learning system significantly impacts children’s learning effectiveness and optimizing user experience.

Virtual reality (VR) is increasingly used as a social platform for users to interact and build connections with one another in an immersive virtual environment. Reflecting on the empirical progress in this area of study, a comprehensive review of how VR could be used to support social interaction is required to consolidate existing practices and identify research gaps to inspire future studies. In this work, we conducted a systematic review of 94 publications in the HCI field to examine how VR is designed and evaluated for social purposes. We found that VR influences social interaction through self-representation, interpersonal interactions, and interaction environments. We summarized four positive effects of using VR for socializing, which are relaxation, engagement, intimacy, and accessibility, and showed that it could also negatively affect user social experiences by intensifying harassment experiences and amplifying privacy concerns. We introduce an evaluation framework that outlines the key aspects of social experience: intrapersonal, interpersonal, and interaction experiences. According to the results, we uncover several research gaps and propose future directions for designing and developing VR to enhance social experience.

… since the authors understood that Scopus database bibliometrics were resulting in Engineering and Human-Computer Interaction, rather than on Industrial and Interaction Design. …

This paper investigates the integration of emotional, cognitive, and interactional processes in the design of educational technologies through the lens of Human–Computer Interaction (HCI). While previous studies have focused on cognitive and interactional engagement, emotional engagement remains underdeveloped in many tools, limiting learning effectiveness. To bridge this gap, this study proposes a theoretical holistic framework integrating usability, emotional intelligence, and adaptive interaction. Through a qualitative analysis, we examine educational platforms—including Duolingo, Khan Academy, and Google Classroom—alongside simulation-based systems such as EduTechRPGs. The study applies Cognitive Load Theory, Emotional Intelligence Theory, and Self-Determination Theory to assess their effectiveness. The findings highlight the importance of designing emotionally intelligent, scalable, and adaptive learning environments, and the proposed framework integrates psychological principles to boost engagement, motivation, and learning outcomes. This study contributes to a learner-centered HCI approach, ensuring that educational technologies support both cognitive and emotional development. Future research should validate the proposed framework empirically and explore interdisciplinary approaches to optimize educational technology. This study highlights the role of HCI in creating meaningful digital learning experiences by integrating psychology, cognitive science, and user experience design.

PURPOSE This review explored the design and application of Artificial Intelligence (AI) technologies supporting neurodiverse users, including individuals with Autism Spectrum Disorder (ASD), ADHD, and dyslexia. It examined system types, application domains, inclusive and adaptive design strategies, user participation, and related ethical challenges. MATERIALS AND METHODS A systematic search across Web of Science, PubMed, ACM Digital Library, IEEE Xplore, and Google Scholar identified studies published between 2019 and 2025. After applying the inclusion criteria and conducting cross-validation, 117 peer-reviewed papers were analysed across five themes: technical features, design strategies, user engagement, effectiveness, and ethical considerations. RESULTS Findings reveal a growing diversity of AI applications in education, healthcare, rehabilitation, and workplace contexts. Multimodal interaction, adaptive feedback, and embodied interfaces enhance engagement and usability; however, research remains fragmented and often lacks long-term perspectives. Most studies lack neurodivergent user participation and fail to adequately address sensory and cognitive heterogeneity, accessibility barriers, and gender bias in their datasets. CONCLUSIONS AI-driven interaction design shows strong potential to enhance inclusivity and personalisation for neurodiverse users. Sustained progress requires interdisciplinary collaboration, participatory co-design, and longitudinal evaluation. Ethical principles, particularly fairness, transparency, and accessibility, should guide the development of future AI systems to ensure equitable, evidence-based support.

This study investigates the cognitive feedback mechanisms enabled by generative AI in creative design processes. A multimodal design platform was developed using joint text–image semantic modeling, and 72 participants completed three rounds of creative tasks on this platform. Behavioral and physiological indices—including AI prompt frequency, reaction time, eye-tracking patterns and task duration—were collected to analyze human–machine interaction dynamics. Process mining and sequence analysis demonstrated that AI intervention accelerated concept generation by approximately 47% and improved semantic consistency scores from 0.64 to 0.89. EEG rhythm analysis further revealed significantly enhanced beta-band activity (p < 0.05), indicating increased cognitive engagement. Meanwhile, AI-mediated feedback reduced average cognitive load by approximately 22% during early-stage idea development, suggesting improved cognitive efficiency. Building on these findings, this work proposes the AI-Cognitive Driven Design System (AICDDS), which characterizes the dynamic interactions among AI prompts, user adjustments and cognitive responses. The system provides a structured mechanism model for optimizing generative AI tools for creative tasks.

Reflection is fundamental to how people make sense of everyday life, helping them navigate moments of growth, uncertainty, and change. Yet in HCI, existing frameworks of designing technologies to support reflection remain narrow, emphasizing cognitive, rational problem-solving, and individual self-improvement. We introduce Daoist philosophy as a non-Western lens to broaden this scope and reimagine reflective practices in interactive systems. Combining insights from Daoist literature with semi-structured interviews with 18 Daoist priests, scholars, and practitioners, we identified three key dimensions of everyday reflection: Stillness, Resonance, and Emergence. These dimensions reveal emergent, embodied, relational, and ethically driven qualities often overlooked in HCI research. We articulate their potential to inform alternative frameworks for interactive systems for reflection, advocating a shift from reflection toward reflecting-with, and highlight the potential of Daoism as an epistemological resource for the HCI community.

Healthcare question-answering (QA) systems can assist physicians in making medical decisions. However, traditional medical QA systems struggle with multi-agents interaction and domain-specific knowledge processing, thereby reducing the accuracy and credibility of clinical decision-making. We thus develop a multi-agent decision-making system by combining a fine-tuned medical model, biomedical knowledge graphs, and PubMed data. By summarizing the symptoms described by users, our system can automatically convene clinical experts from various fields, retrieve domain knowledge, and provide clinical decision support for users. We have validated the system performance using both technical and user-centric approaches in terms of information accuracy, user satisfaction, user trust, ect. We thus provide an effective tool for healthcare professionals to make accurate and timely decisions. Furthermore, this study also reveals new design and research opportunities, including (1) optimizing multi-agent collaboration mechanisms for more complex medical decision-making, (2) improving interaction design to enhance system transparency and explainability, and (3) expanding the system to support a broader range of medical issues and multimodal data.

… in the field of Human Computer Interaction (HCI) that relates … of design practices most commonly used in the field of HCI to … fill that gap by analyzing design trends engaging non-expert …

Abstract The iteration of AI technology has enhanced the industry competitiveness of sports apps and brought a new emotional experience to users. However, the community function of AI-enabled sports apps has not yet received sufficient attention. This study adopts the technology acceptance model framework through the human-computer interaction and social psychology perspectives, incorporating perceived interactivity (human-human interaction, human-information interaction, human-system interaction), user experience (functional experience, content experience, and emotional experience), attachment theory (emotional attachment, emotional loyalty), social identity, social trust, and satisfaction variables to construct a theoretical model. It aims to solve the problem of how AI can enhance users’ emotional interaction, community stickiness, and ultimately social interaction satisfaction in sports apps. Through literature review, theoretical analysis, and case study, the Chinese “KEEP” APP was identified as the research object, and the questionnaire was constructed with an improved test scale. The study used a cross-sectional sampling method to collect data from Chinese online platforms for three months (N = 520) and tested the hypotheses in the theoretical model through structural equation modeling and artificial neural networks. The results of the study show that (1) emotional attachment, emotional loyalty, social identity, and social trust positively and significantly affect user satisfaction; (2) emotional attachment and social identity positively and significantly affect human-human interaction; (3) perceived usefulness, social identity, and social trust significantly construct an influence loop on the internal path. Compared with existing studies, this study proposes a multidimensional innovative framework that reveals the deeper influence mechanism of AI technology in sports APP communities and makes up for the shortcomings of existing studies in terms of users’ emotional interactions and community stickiness. Through this study, sports APP developers and operators, marketers, AI technology developers, as well as sports enthusiasts, and general users can obtain specific practical suggestions to further optimize the design and functionality of sports apps, and enhance the overall user experience and satisfaction.

HCI researchers recognize affect and emotion as fundamental parts of human experience however conceptualizing emotions as ineffable, embodied, situated, or culturally bound does not fit within some of the dominant paradigm of Affective computing and emotion AI research focused mostly on recognition and classification of basic emotions. An alternative term, Affective Interaction, has emerged to bring together a growing body of research which treats emotion and affect within HCI in similar ways. This workshop brings the research community together to examine various perspectives on affect, and specifically contrast Affective Interaction with Affective Computing. The aim is to discuss opportunities and limitations associated with each perspective, reconcile with advances in the science of emotion, and to speculate on future research directions. We believe that bringing together HCI researchers around Affective Interaction is vitally important because the broad reach of Affective Computing techniques may be obscuring advances in emotion research that show evidence that emotion defies easy categories and is culturally situated.

As artificial intelligence (AI) continues to reshape the workforce, its current trajectory raises pressing questions about its ultimate purpose. Why does job automation dominate the agenda, even at the expense of human agency and equity? This paper critiques the automation-centric paradigm, arguing that current reward structures, which largely focus on cost reduction, drive the overwhelming emphasis on task replacement in AI patents. Meanwhile, Human-Centered AI (HCAI), which envisions AI as a collaborator augmenting human capabilities and aligning with societal values, remains a fugitive from the mainstream narrative. Despite its promise, HCAI has gone “missing”, with little evidence of its principles translating into patents or real-world impact. To increase impact, actionable interventions are needed to disrupt existing incentive structures within the HCI community. We call for a shift in priorities to support translational research, foster cross-disciplinary collaboration, and promote metrics that reward tangible and real-world impact.

Large language models (LLMs) are increasingly used for analytical tasks, yet their effectiveness in real-world applications remains underexamined, partly due to the opacity of proprietary models. We evaluate ChatGPT (GPT-3.5 and GPT-4) on the practical task of extracting research challenges from a large scholarly corpus in Human-Computer Interaction (HCI). Using a two-step approach, we first apply GPT-3.5 to extract candidate challenges from the 879 papers in the 2023 ACM CHI Conference proceedings, then use GPT-4 to select the most relevant challenges per paper. This process yielded 4,392 research challenges across 113 topics, which we organized through topic modeling and present in an interactive visualization. We compare the identified challenges with previously established HCI grand challenges and the United Nations Sustainable Development Goals, finding both strong alignment in areas such as ethics and accessibility, and gaps in areas such as human-AI collaboration. A task-specific evaluation with human raters confirmed near-perfect agreement that the extracted statements represent plausible research challenges (\k{appa} = 0.97). The two-step approach proved cost-effective at approximately US$50 for the full corpus, suggesting that LLMs offer a practical means for qualitative text analysis at scale, particularly for prototyping research ideas and examining corpora from multiple analytical perspectives.

Interactive AI systems, including search engines, recommender systems, conversational agents, and generative AI applications, are increasingly central to user experiences. However, rigorously evaluating their performance, training them effectively with interaction data, and modeling user behavior for personalization remain significant challenges, often difficult to address reproducibly and at scale. User simulation, which employs intelligent agents to mimic human interaction patterns, offers a powerful and versatile methodology to tackle these interconnected issues. This half-day tutorial provides a comprehensive overview of modern user simulation techniques for interactive AI systems. We will explore the theoretical foundations and practical applications of simulation for system evaluation, algorithm training, and user modeling, emphasizing the crucial connections between these uses. The tutorial covers key simulation methodologies, with a particular focus on recent advancements leveraging large language models, discussing both the opportunities they present and the open challenges they entail. Crucially, we will also provide practical guidance, highlighting relevant toolkits, libraries, and datasets available to researchers and practitioners.

… As the customer experience or “user experience,” as we prefer to call it in this article, is seen as a key success factor to ultimately be selected as a supplier in the B2B decision-making …

Abstract Despite the influx of research examining various aspects of mobile-assisted language learning (MALL) applications (apps) over the past two decades, there have been no head-to-head studies that have investigated the comparative effectiveness of different mobile apps. The current study addresses this gap by directly comparing two of the most well-researched and popular MALL apps: Babbel and Duolingo. In this mixed methods study, adult learners (N = 59) engaged in studying Turkish as a foreign language using either Babbel (n = 27) or Duolingo (n = 32) for eight weeks. Participants then completed two exit assessments, including (1) a posttest gauging their development of various language skills (i.e. reading, writing, speaking, listening, vocabulary, and grammatical competence), and (2) a survey assessing their user experience (e.g. enjoyment, motivation, beliefs about effectiveness). The results of this study showed that although both the Babbel and Duolingo groups made progress, there were no statistically significant differences between their L2 learning gains. However, for the Babbel group, there was a stronger correlation between participants’ study time and their posttest scores. Finally, Babbel users also felt the app was more effective for learning grammar, speaking/pronunciation skills, and for learning about the target language culture. This study discusses the implications of these findings for researchers and MALL users more broadly.

Traditional AI-assisted decision-making systems often provide fixed recommendations that users must either accept or reject entirely, limiting meaningful interaction—especially in cases of disagreement. To address this, we introduce Human-AI Deliberation, an approach inspired by human deliberation theories that enables dimension-level opinion elicitation, iterative decision updates, and structured discussions between humans and AI. At the core of this approach is Deliberative AI, an assistant powered by large language models (LLMs) that facilitates flexible, conversational interactions and precise information exchange with domain-specific models. Through a mixed-methods user study, we found that Deliberative AI outperforms traditional explainable AI (XAI) systems by fostering appropriate human reliance and improving task performance. By analyzing participant perceptions, user experience, and open-ended feedback, we highlight key findings, discuss potential concerns, and explore the broader applicability of this approach for future AI-assisted decision-making systems.

Purpose The purpose of this paper is to explore user engagement (UE) within the Metaverse (MV) environment, emphasising the crucial role of immersive experiences (IEs). This study aims to understand how IEs influence UE and the mediating effects of hedonic value (HV) and utilitarian value (UV) on this relationship. Additionally, the authors examine the moderating impacts of user perceptions (UPs) such as headset comfort, simulation sickness, prior knowledge and ease of use on the utilisation of the MV. This study seeks to elucidate the dynamics of virtual travel at a pre-experience stage, enhancing the comprehension of how digital platforms can revolutionise UE in travel and tourism. Design/methodology/approach This study used a triangulation methodology to provide a thorough investigation into the factors influencing UE in the MV. A systematic literature review (SLR) was conducted to frame the research context and identify relevant variables. To gather empirical data, 25 interviews were performed with active MV users, supplemented by a survey distributed to 118 participants. The data collected was analysed using structural equation modelling (SEM) to test the hypothesised relationships between IEs, UPs, HV and UV and their combined effect on UE within the MV. Findings The findings from the SEM indicate that engaging in the MV leads to a positive IE, which significantly enhances UE. Additionally, it was discovered that HV and UV play a mediating role in strengthening the link between IEs and UE. Furthermore, UPs, including headset comfort, simulation sickness, prior knowledge and ease of use, are significant moderators in the relationship between IEs and MV usage. These insights provide a nuanced understanding of the variables that contribute to and enhance UE in virtual environments. Originality/value This research contributes original insights into the burgeoning field of digital tourism by focusing on the MV, a rapidly evolving platform. It addresses the gap in the existing literature by delineating the complex interplay between IEs, UPs and value constructs within the MV. By using a mixed-method approach and advanced statistical analysis, this study provides a comprehensive model of UE specific to virtual travel platforms. The findings are particularly valuable for developers and marketers in the hospitality and tourism sectors seeking to capitalise on digital transformation and enhance UE through immersive technologies.

The concept of Operator 4.0 has been recently defined to evolve the modern industrial scenarios by defining a knowledge sharing process from/to operators and industrial systems, creating personalized skills, and introducing digital tools towards socially sustainable factories. In this context, dynamic and adaptive user interfaces can make humans part of the intelligent factory system, supporting human work contextually and providing specific contents when needed, preserving the human wellbeing. This paper defines a human-centric methodology for the symbiotic co-evolution of operators ’ skills, assistive digital tools and user interfaces, developed within the Horizon Europe project titled “ DaCapo - Digital assets and tools for Circular value chains and manufacturing products ” . The project focuses on defining a new set of human-centric digital tools and services for the manufacturing industry capable of boosting the application of circular economy (CE) throughout the manufacturing value chains. The proposed methodology can link the specific needs of an industrial case to the definition of the most proper assistive digital tools and functionalities to drive the design of adaptive, proactive user interfaces for the Operator 4.0. The method has been applied and validated on one of the project use cases, involving a manufacturing company operating in warehousing and logistics.

Abstract In the past five years, the textile industry has undergone significant transformations in response to evolving fashion trends and increased consumer garment turnover. To address the environmental impacts of fast fashion, the industry is embracing artificial intelligence (AI) and immersive technologies, particularly leveraging conversational agents as personalized guides for sustainable fashion practices. In this research article, we conduct a systematic literature review to categorize techniques, platforms, and applications of conversational agents in promoting sustainability within the fashion industry. Additionally, the review aims to scrutinize the solutions offered, identify gaps in the existing literature, and provide insights into the effectiveness and limitations of these conversational agents. Utilizing a predefined search strategy on IEEE Xplore, Google Scholar, SCOPUS, and Web of Science, 15 relevant articles were selected through a step-by-step procedure based on the guidelines of the PRISMA framework. The findings reveal a notable global interest in AI-powered conversational agents, with Italy emerging as a significant center for research in this domain. The studies predominantly focus on consumer perceptions and intentions regarding the adoption of AI technologies, indicating a broader curiosity about how individuals incorporate such innovations into their daily lives. Moreover, a substantial proportion of the studies employ diverse methods, reflecting a comprehensive approach to understanding the functionality and performance of conversational agents in various contexts. While acknowledging the historical precedence of text-based agents, the review highlights a research gap related to embodied agents. The conclusion emphasizes the need for continued exploration, particularly in understanding the broader impact of these technologies on creating sustainable and environmentally friendly business models in the e-retail sector.

… User experience practitioners should also find this book useful and inspiring as a starting point in their … Centered Design methodology, which is the prerequisite for conducting any IA/…

As a cornerstone of modern information access, search engines have become indispensable in everyday life. With the rapid advancements in AI and natural language processing (NLP) technologies, particularly large language models (LLMs), search engines have evolved to support more intuitive and intelligent interactions between users and systems. Conversational search, an emerging paradigm for next-generation search engines, leverages natural language dialogue to facilitate complex and precise information retrieval, thus attracting significant attention. Unlike traditional keyword-based search engines, conversational search systems enhance user experience by supporting intricate queries, maintaining context over multi-turn interactions, and providing robust information integration and processing capabilities. Key components such as query reformulation, search clarification, conversational retrieval, and response generation work in unison to enable these sophisticated interactions. In this survey, we explore the recent advancements and potential future directions in conversational search, examining the critical modules that constitute a conversational search system. We highlight the integration of LLMs in enhancing these systems and discuss the challenges and opportunities that lie ahead in this dynamic field. Additionally, we provide insights into real-world applications and robust evaluations of current conversational search systems, aiming to guide future research and development in conversational search.

The convergence of Virtual Reality (VR), Artificial Intelligence (AI), and the Internet of Things (IoT) offers transformative potential across numerous sectors. However, existing studies often examine these technologies independently or in limited pairings, which overlooks the synergistic possibilities of their combined usage. This systematic review adheres to the PRISMA guidelines in order to critically analyze peer-reviewed literature from highly recognized academic databases related to the intersection of VR, AI, and IoT, and identify application domains, methodologies, tools, and key challenges. By focusing on real-life implementations and working prototypes, this review highlights state-of-the-art advancements and uncovers gaps that hinder practical adoption, such as data collection issues, interoperability barriers, and user experience challenges. The findings reveal that digital twins (DTs), AIoT systems, and immersive XR environments are promising as emerging technologies (ET), but require further development to achieve scalability and real-world impact, while in certain fields a limited amount of research is conducted until now. This review bridges theory and practice, providing a targeted foundation for future interdisciplinary research aimed at advancing practical, scalable solutions across domains such as healthcare, smart cities, industry, education, cultural heritage, and beyond. The study found that the integration of VR, AI, and IoT holds significant potential across various domains, with DTs, IoT systems, and immersive XR environments showing promising applications, but challenges such as data interoperability, user experience limitations, and scalability barriers hinder widespread adoption.

Autonomous Graphical User Interface (GUI) navigation agents can enhance user experience in communication, entertainment, and productivity by streamlining workflows and reducing manual intervention. However, prior GUI agents often trained with datasets comprising tasks that can be completed within a single app, leading to poor performance in cross-app navigation. To address this problem, we present GUIOdyssey, a comprehensive dataset for crossapp mobile GUI navigation. GUIOdyssey comprises 8,334 episodes with an average of 15.3 steps per episode, covering 6 mobile devices, 212 distinct apps, and 1,357 app combinations. Each step is enriched with detailed semantic reasoning annotations, which aid the model in building cognitive processes and enhancing its reasoning abilities for complex cross-app tasks. Building on GUIOdyssey, we develop OdysseyAgent, an exploratory multimodal agent for long-step cross-app navigation equipped with a history resampler module that efficiently attends to historical screenshot tokens, balancing performance and inference speed. Extensive experiments conducted in both in-domain and out-of-domain scenarios validate the effectiveness of our approach. Moreover, we demonstrate that historial information involving actions, screenshots and context in our dataset can significantly enhances OdysseyAgent's performance on complex cross-app tasks.

: Artificial intelligence (AI) has made the wave of data analytics extremely fast in processing and interpreting huge datasets. AI can help with automated parts of data collection and initial analysis, but strategic decisions made during A/B testing need human judgment and experience. The paper will touch upon analyzing current trends and challenges and investigate case studies, the complementary relationship between AI technologies and human expertise, and, hence, the need for an approach that optically intermingles the strength of both to reach informed and effective decision-making. Businesses and industries worldwide use split testing or A/B testing as their main research method to check how separate web page designs work against each other. Business case studies confirm that AI improves all industries by handling complex datasets to find important details beyond BI systems. The case results show what AI and other analytical tools can do well and poorly in making business choices. Using AI technology together with BI tools as part of a human-led system creates the best solution for businesses to use data effectively while keeping decisions traceable.

Performing effective gene-editing experiments requires a deep understanding of both the CRISPR technology and the biological system involved. Meanwhile, despite their versatility and promise, large language models (LLMs) often lack domain-specific knowledge and struggle to accurately solve biological design problems. We present CRISPR-GPT, an LLM agent system to automate and enhance CRISPR-based gene-editing design and data analysis. CRISPR-GPT leverages the reasoning capabilities of LLMs for complex task decomposition, decision-making and interactive human–artificial intelligence (AI) collaboration. This system incorporates domain expertise, retrieval techniques, external tools and a specialized LLM fine tuned with open-forum discussions among scientists. CRISPR-GPT assists users in selecting CRISPR systems, experiment planning, designing guide RNAs, choosing delivery methods, drafting protocols, designing assays and analysing data. We showcase the potential of CRISPR-GPT by knocking out four genes with CRISPR-Cas12a in a human lung adenocarcinoma cell line and epigenetically activating two genes using CRISPR-dCas9 in a human melanoma cell line. CRISPR-GPT enables fully AI-guided gene-editing experiment design and analysis across different modalities, validating its effectiveness as an AI co-pilot in genome engineering. An agent-based large language model (LLM) tool helps with CRISPR-based gene-editing experimental design and analysis.

… Human–AI collaboration (HAIC) and KEco exhibit a mutually … robust ecosystems inform collaborative practices through … Exploring future human-AI interaction through high fidelity …

As Artificial Intelligence (AI) becomes increasingly embedded in high-stakes domains such as healthcare, law, and public administration, automation bias (AB)—the tendency to over-rely on automated recommendations—has emerged as a critical challenge in human–AI collaboration. While previous reviews have examined AB in traditional computer-assisted decision-making, research on its implications in modern AI-driven work environments remains limited. To address this gap, this research systematically investigates how AB manifests in these settings and the cognitive mechanisms that influence it. Following PRISMA 2020 guidelines, we reviewed 35 peer-reviewed studies from SCOPUS, ScienceDirect, PubMed, and Google Scholar. The included literature, published between January 2015 and April 2025, spans fields such as cognitive psychology, human factors engineering, human–computer interaction, and neuroscience, providing an interdisciplinary foundation for our analysis. Traditional perspectives attribute AB to over-trust in automation or attentional constraints, resulting in users perceiving AI-generated outputs as reliable. However, our review presents a more nuanced view. While confirming some prior findings, it also sheds light on additional interacting factors such as, AI literacy, level of professional expertise, cognitive profile, developmental trust dynamics, task verification demands, and explanation complexity. Notably, although Explainable AI (XAI) and transparency mechanisms are designed to mitigate AB, overly technical, cognitively demanding, or even simplistic explanations may inadvertently reinforce misplaced trust, especially among less experienced professionals with low AI literacy. Taken together, these findings suggest that although explanations may increase perceived system acceptability, they are often insufficient to improve decision accuracy or mitigate AB. Instead, user engagement emerges as the most feasible and impactful point of intervention. As increased verification effort has been shown to reduce complacency toward AI mis-recommendations, we propose explanation design strategies that actively promote critical engagement and independent verification. These conclusions offer both theoretical and practical contributions to bias-aware AI development, underscoring that explanation usability is best supported by features such as understandability and adaptiveness.

Artificial intelligence (AI) systems, evolving from reactive tools to proactive collaborators, reshape team dynamics in today's digital workplaces. Text‐based collaboration now frequently involves AI participants that perform tasks traditionally handled by humans, such as creative problem‐solving and decision‐making. This transition has been linked to changes in group dynamics, particularly in relation to social presence, which appears to shape the patterns of productivity and collaboration. We conducted three empirical studies on human–AI teams to investigate the relationship between social presence and willingness to depend on teammates, team‐oriented commitment, and motivation to contribute. Drawing on social presence theory and theory of planned behaviour, our results show that while social presence has a direct association with motivation to contribute, an equally important indirect pathway is associated with human factors like team‐oriented commitment and team members' willingness to depend on each other. We show that while social presence is significantly associated with behavioural intentions, greater AI familiarity and understandability are associated with a stronger relationship, raising questions about the sufficiency of relying solely on anthropomorphic features. Our study contributes to the understanding of human–AI collaboration in social presence research, highlighting the importance of considering social and interpersonal processes in hybrid teams. Our findings have managerial implications for organizations looking to adopt AI‐based systems for collaboration.

We introduce SciSciGPT, an open-source, prototype artificial intelligence (AI) collaborator that uses the domain of science of science as a testbed to explore the potential of large language model-powered research tools. SciSciGPT automates complex workflows, supports diverse analytical approaches, accelerates research prototyping and iteration and facilitates reproducibility. Through case studies, we demonstrate its ability to streamline a wide range of empirical and analytical research tasks while highlighting its broader potential to advance research. We further propose a large language model agent capability maturity model for human–AI collaboration, envisioning a roadmap to further improve and expand upon frameworks such as SciSciGPT. As AI capabilities continue to evolve, frameworks such as SciSciGPT may play increasingly pivotal roles in scientific research and discovery. At the same time, these new advances also raise critical challenges, from ensuring transparency and ethical use to balancing human and AI contributions. Addressing these issues may shape the future of scientific inquiry and inform how we train the next generation of scientists to thrive in an increasingly AI-integrated research ecosystem.

As AI decision support systems play a growing role in high-stakes decision making, ensuring effective integration of human intuition with AI recommendations is essential. Despite advances in AI explainability, challenges persist in fostering appropriate reliance. This review explores AI decision support systems that enhance human intuition through the analysis of 84 studies addressing three questions: (1) What design strategies enable AI systems to support humans’ intuitive capabilities while maintaining decision-making autonomy? (2) How do AI presentation and interaction approaches influence trust calibration and reliance behaviors in human–AI collaboration? (3) What ethical and practical implications arise from integrating AI decision support systems into high-risk human decision making, particularly regarding trust calibration, skill degradation, and accountability across different domains? Our findings reveal four key design strategies: complementary role architectures that amplify rather than replace human judgment, adaptive user-centered designs tailoring AI support to individual decision-making styles, context-aware task allocation dynamically assigning responsibilities based on situational factors, and autonomous reliance calibration mechanisms empowering users’ control over AI dependence. We identified that visual presentations, interactive features, and uncertainty communication significantly influence trust calibration, with simple visual highlights proving more effective than complex presentation and interactive methods in preventing over-reliance. However, a concerning performance paradox emerges where human–AI combinations often underperform the best individual agent while surpassing human-only performance. The research demonstrates that successful AI integration in high-risk contexts requires domain-specific calibration, integrated sociotechnical design addressing trust calibration and skill preservation simultaneously, and proactive measures to maintain human agency and competencies essential for safety, accountability, and ethical responsibility.

Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We created and evaluated five collaborative AI agents with strategies that differ in the manner and degree they adapt to human actions. Participants interacted with a subset of these agents, evaluated their perceived traits, and selected their preferred agent. We used a Bayesian model to understand how agents’ strategies influence the human–AI team performance, AI’s perceived traits, and the factors shaping human preferences in pairwise agent comparisons. Our results show that agents who are more considerate of human actions are preferred over purely performance-maximizing agents. Moreover, we show that such human-centric design can improve the likability of AI collaborators without reducing performance. We find evidence for inequality-aversion effects being a driver of human choices, suggesting that people prefer collaborative agents which allow them to meaningfully contribute to the team. Taken together, these findings demonstrate how collaboration with AI can benefit from development efforts, which include both subjective and objective metrics. Human-AI collaboration is expected to grow in the coming years. Particular attention is being paid to agentic cooperative AI that is capable of autonomously performing helpful tasks without repeated human instruction due to its potential to significantly improve the performance of human-AI teams. However, the use of cooperative AI agents poses two key challenges: (1) the development of such agents in modern multiagent reinforcement learning paradigms often excludes human collaborators, and (2) the process of integrating human preferences into the algorithms underlying AI agents remains poorly understood. Our study addresses these shortcomings by establishing an empirical framework to evaluate how algorithmic changes can be mapped to human preferences. Our study reveals key dynamics, such as algorithm changes that increase human liking of the AI agent without harming the performance of the human-AI team, and a pronounced human preference for inequity-aversion. These findings inform human-AI development by demonstrating how collaborative AI can be both effective and enjoyable. Our approach adjusts agent behavior by modifying algorithmic inputs and outputs, making it broadly applicable to new and existing agentic systems

… human-AI interaction, creating new opportunities and challenges for HumanCentered AI (HCAI). This chapter establishes human-AI co-creation as a new interaction … social collaboration. …

PurposeHuman-artificial intelligence (AI) collaboration, as a new form of cooperative interaction, has been applied in brainstorming activities. This study aims to explore the impact of performance-reward expectancy (PRE) and creative motivation (CM), along with the search for ideas in associative memory (SIAM) theory, on participants' AI collaboration intent (AICI).Design/methodology/approachThe research employs an online survey targeting users with brainstorming experience. Structural equation modeling (SEM) is applied to analyze the data and validate the proposed hypotheses.FindingsPRE shows a positive correlation with both intrinsic motivation (IM) and extrinsic motivation (EM). Furthermore, EM significantly and positively influences AICI, while IM has a negative significant effect. Additionally, the study confirms the mediating role of social inhibition (SI) between EM and AICI.Research limitations/implicationsThis study examines the intent to collaborate with AI in brainstorming, filling a gap in existing research. It integrates SIAM theory to analyze how performance rewards and creative motivation influence this intent. Findings reveal that performance-based rewards effectively motivate creative engagement, but high intrinsic motivation may lead to lower intent to collaborate due to autonomy concerns and trust issues. The study emphasizes the need for an open environment and offers practical insights for fostering AI collaboration while addressing challenges like social inhibition and resistance among participants.Practical implicationsThis study provides practical insights for creative teams and individuals, emphasizing the importance of integrating AI in brainstorming to unlock its full potential. While performance rewards are effective, social inhibition may still lead participants to have negative attitudes toward AI collaboration. Creating an open and inclusive environment is essential. Additionally, the “individual + AI” model may provoke resistance among highly intrinsically motivated participants, necessitating training and improved AI transparency to build trust. Although focused on the Chinese market, the findings are applicable globally, highlighting the need to explore effective AI integration methods for innovation.Social implicationsOur study found that PRE can positively influence intrinsic and extrinsic motivation in creative activities. This finding provides new evidence for our understanding of the role of performance-reward mechanisms in stimulating creativity. At the same time, we also explored how factors such as social inhibition and production blocking can affect individuals’ willingness to work with AI by influencing creativity motivation. This provides new insights to better understand how AI in teams affects individual psychology and team dynamics. These findings not only enrich our understanding of innovation and teamwork but also provide valuable references and directions for future research.Originality/valueThis study systematically examines the influence of PRE on CM within the context of AI-assisted brainstorming for the first time. It further investigates how SIAM theory regulates this process and ultimately shapes participants' willingness to engage in AI collaboration. The findings offer theoretical and practical guidance on designing incentive mechanisms to enhance engagement in AI-supported brainstorming and provide new perspectives on the application of AI in team innovation activities.

As AI assistance becomes embedded in programming practice, researchers have increasingly examined how these systems help learners generate code and work more efficiently. However, these studies often position AI as a replacement for human collaboration and overlook the social and learning-oriented aspects that emerge in collaborative programming. Our work introduces human-human-AI (HHAI) triadic programming, where an AI agent serves as an additional collaborator rather than a substitute for a human partner. Through a within-subjects study with 20 participants, we show that triadic collaboration enhances collaborative learning and social presence compared to the dyadic human–AI (HAI) baseline. In the triadic HHAI conditions, participants relied significantly less on AI generated code in their work. This effect was strongest in the HHAI-shared condition, where participants had an increased sense of responsibility to understand AI suggestions before applying them. These findings demonstrate how triadic settings activate socially shared regulation of learning by making AI use visible and accountable to a human peer, suggesting that AI systems that augment rather than automate peer collaboration can better preserve the learning processes that collaborative programming relies on.

Abstract Advancements in AI’s conversational capabilities and situational awareness mean that now, humans work with AI collaboratively. However, these developments affect the skills needed to use AI effectively. In this study, we address the need to update measures of AI-related knowledge and skills to reflect the collaborative capability of advanced AI tools by developing and validating two new scales focusing on collaboration and metacognition. A survey of 292 users of collaborative AI tools was conducted. Both the Collaborative AI Literacy and Collaborative AI Metacognition scales showed good internal consistency and predictive validity. Structural equation modeling supported their convergent and discriminant validity. Both measures correlated with users’ assessments of the benefits from working with collaborative AI tools. As predicted, Collaborative AI Metacognition explained significant variance beyond that explained by general Metacognition. These validated scales provide an important resource for assessing and researching knowledge and skills for working with Collaborative AI tools.

The abilities that recent AI models presented, like multi-modal content generation and reasoning, allow us to see the possibility of human-AI collaboration. However, enabling AI to act proactively and harmoniously in collaboration still faces challenges, and aspects like the optimal action timing and collaboration dynamism, await to be explored. Exploring these aspects is important to designing adaptive AI to enhance the human-AI collaboration experience and system usability. In this study, we cut in from the collaboration level and view human-AI collaboration as mixed-focus collaboration to focus on human’s transitions between independent and collaborative works. Grounded on previous studies in human-human collaboration, we identified four coupling styles and seven types of transition cues in human-AI collaboration, serving as preliminary results for future studies. We envisioned how our results could be further extended to support the design of adaptive AI, hoping to enhance human-AI collaboration experience and the usability of collaborative systems.

Within journalistic editorial processes, disclosing AI usage is currently limited to simplistic labels, which misses the nuance of how humans and AI collaborated on a news article. Through co-design sessions (N=10), we elicited 69 disclosure designs and implemented four prototypes that visually disclose human–AI collaboration in journalism. We then ran a within-subjects lab study (N=32) to examine how disclosure visualizations (Textual, Role-based Timeline, Task-based Timeline, Chatbot) and collaboration ratios (Primarily Human vs. Primarily AI) influenced visualization perceptions, gaze patterns, and post-experience responses. We found that textual disclosures were least effective in communicating human-AI collaboration, whereas Chatbot offered the most in-depth information. Furthermore, while role-based timelines amplified AI contribution in primarily human articles, task-based timeline shifted perceptions toward human involvement in primarily AI articles. We contribute Human-AI collaboration disclosure visualizations and their evaluation, and cautionary considerations on how visualizations can alter perceptions of AI’s actual role during news article creation.

With the increasing application of GenAI in education, researchers and practitioners are paying more and more attention to its effectiveness and impact in teaching and learning. This can be evidenced by the increasing number of literature reviews on this topic published in recent years. However, these literature reviews seldom analysed the effectiveness of GenAI‐powered educational applications from the human–AI interaction perspective, which is a widely recognized critical factor influencing the effectiveness of such GenAI‐powered educational applications. In response, this study systematically reviews 56 empirical studies on the application of GenAI in education. To explicitly address this gap from the human–AI interaction perspective, we analysed the reviewed studies using the AIED‐HCD framework, which conceptualizes three human–AI interaction modes along the dimensions of human control and AI automation, and examined educational contextual factors and educational tasks supported by GenAI to assess how interaction modes vary across teaching and learning contexts. In addition, we conducted a sensitivity analysis to evaluate the robustness of findings across these modes. We demonstrated that, although current educational practices remain cautious towards interaction modes with a high level of AI automation, the mode characterized by both high human control and high AI automation has begun to emerge as a trend, demonstrating promising potential for integrating the respective strengths of humans and AI. Furthermore, sensitivity analysis reveals that many studies lack sufficient detail in their statistical reporting, and the reported effect sizes often fall below the thresholds required for acceptable statistical power. Based on these findings, we recommend: (i) beyond exploring how to improve the practical use of AI automation under human supervision and control, educational researchers and practitioners should carefully choose and implement suitable human–AI interaction settings according to the specific context of use, with higher levels of AI automation applied only when supported by appropriate task design and pedagogical guidance; (ii) researchers should improve methodological transparency by estimating appropriate sample sizes and testing assumptions to ensure the reliability of empirical findings. Generative artificial intelligence can efficiently analyse vast amounts of textual information and perform complex natural language processing and generation tasks, demonstrating powerful language intelligence capabilities. Generative artificial intelligence is increasingly being integrated into various educational systems, and with its exceptional capabilities, its potential to support educational applications is gradually being explored and put into practice. Based on the AIED‐HCD conceptual framework, this study systematically classifies current GenAI‐based empirical research by examining two key dimensions, namely the extent to which human control and automation through GenAI are enabled, and offers a holistic perspective on the current state of research. A sensitivity analysis was conducted to examine whether the empirical evidence reported in current GenAI‐based studies demonstrates sufficient statistical power to support future research and practical implementation. Stay continuously informed about the latest advancements in AI technologies and carefully verify their suitability for different interaction modes to enhance educational user experiences and deliver systematically measurable improvements and efficiencies to the educational landscape. Current GenAI‐based empirical studies should include more detailed statistical reporting, such as whether assumption tests were conducted and the specific results of effect sizes, to support empirical evidence and enhance transparency.

In mixed reality environments, virtual objects can obscure real-world obstacles, creating a risk of collision when users walk through them. Although users may choose to detour around virtual objects, this behavior also carries risks, such as colliding with obstacles or pedestrians along the detour route. To reduce collision risks, it is essential to understand the factors that determine whether users walk through or detour, as well as the walking paths associated with each behavior. In this research, we investigated users’ walking behavior toward both a static virtual obstacle and a virtual obstacle that disappeared as the user approached. Our findings suggest that individual characteristics and the width of the virtual obstacle influence the decision to walk through or detour. Furthermore, while most users initially chose paths that detoured around the virtual obstacle, once the obstacle began to disappear, they switched their walking paths toward the space where it had been.

… users to quickly construct, sketching, manipulate and reshape spatial elements in mixed reality… , the following research question (RQ) is proposed: How can mixed reality enhance early …

Spaces shared by Mixed Reality (MR) users and bystanders (non-MR users) pose unique challenges because bystanders cannot see the virtual interfaces that the MR user is interacting with. As a result, they may unknowingly occlude these interfaces, leading to physical-virtual conflicts that disrupt the MR user’s experience. To address this issue, we explore how projecting shadows of virtual interfaces onto the floor can enhance bystander awareness. We conducted a user study (N = 20) in which a bystander performed an independent task in the same space as an MR user. The bystander experienced one of three visualization conditions - none (no projection), dynamic (shadows appear only upon collision), and always-on (shadows of all interfaces are continuously visible). Our findings show that always-on significantly mitigated physical-virtual conflicts and was most preferred by participants. In contrast, the dynamic condition was found to be distracting, while none required extra communication and led to more interference. Our results highlight the value of persistent, easily perceived cues for bridging the perceptual divide between MR users and bystanders in shared physical spaces, ultimately promoting more seamless integration of MR systems into everyday environments.

In education and training, Mixed Reality (MR) is a thriving technology leveraged to enhance engagement and collaboration, and to maximize learning outcomes. However, there is no …

… enhanced user experiences, and the importance of user involvement in the model generation process. We also discuss future research to improve the technology’s capabilities and user…

This paper investigates the challenges of designing mixed-presence environments for Mixed Reality and suggests future research directions derived from an expert workshop. Developing mixed-presence systems is a complex undertaking that combines the intricacies of both co-located and distributed mixed-reality spaces. Current literature in this field describes various promising design and development approaches but lacks a systematic overview, resulting in fragmented solutions to re-occurring challenges. Therefore, we conducted a comprehensive review of mixed-presence and multi-user remote mixed-reality systems, categorizing the prevalent challenges faced during the development of such systems, but also current trends, common use cases, study tasks and methodologies. Supported by these results, we then conducted an expert ideation workshop to collect and structure promising future research directions. As a result, we provide a detailed resource to orient and prepare developers for probable challenges and support researchers in making informed design decisions for future mixed-presence studies in Mixed Reality.

Drinking is an inherently multisensory activity, yet the potential of immersive technology to dynamically shape flavor experiences remains underexplored in Human-Food Interaction (HFI) research. We introduce “XTea”, an adaptive beverage cup-based system that integrates large language models to translate natural language input into modifications of a parameterized immersive environment experienced through a headset when drinking bubble tea. Through a study with 12 bubble tea enthusiasts, we derived themes that demonstrate how “XTea” can enrich sensory engagement, support personalized and agentic experiences, and foster social qualities of drinking, pointing toward new explorations for multisensory HFI design. We also present four design strategies for multisensory beverage experiences. Ultimately, we aim to contribute to the advancement of HFI research on how multisensory interaction design can enrich flavor perception and engagement.

We investigate hybrid user interfaces (HUIs), aiming to establish a cohesive understanding and to adopt consistent terminology for this nascent research area. HUIs combine heterogeneous devices in complementary roles, leveraging the distinct benefits of each. Our work focuses on cross-device interaction between 2D devices and mixed reality environments, which are particularly compelling, leveraging the familiarity of traditional 2D platforms while providing spatial awareness and immersion. Although prior work has prominently explored such HUIs in the context of mixed reality, we still lack a cohesive understanding of the unique design possibilities and challenges of such combinations, resulting in a fragmented research landscape. We conducted a systematic survey and present a taxonomy of HUIs that combine conventional display technology and mixed reality environments. Based on this, we discuss past and current challenges, the evolution of definitions, and prospective opportunities to tie together the past 30 years of research with our vision of future HUIs.

Object selection in Mixed Reality (MR) becomes particularly challenging in dense or occluded environments, where traditional mid-air ray-casting often leads to ambiguity and reduced precision. We present two complementary techniques: (1) a real-time Bézier Curve selection paradigm guided by finger curvature, enabling expressive one-handed trajectories, and (2) an on-body disambiguation mechanism that projects the four nearest candidates onto the user’s forearm via proximity-based mapping. Together, these techniques combine flexible, user-controlled selection with tactile, proprioceptive disambiguation. We evaluated their independent and joint effects in a 2 × 2 within-subjects study (N = 24), crossing interaction paradigm (Bézier Curve vs. Linear Ray) with interaction medium (Mid-air vs. On-body). Results show that on-body disambiguation significantly reduced selection errors and physical demand while improving perceived performance, hedonic quality, and user preference. Bézier input provided effective access to occluded targets but incurred longer task times and greater effort under some conditions. We conclude with design implications for integrating curved input and on-body previews to support precise, adaptive selection in immersive environments.

Board games often involve strategic decision making and procedural planning tasks. Such tasks require learners to make decisions based on dynamically evolving game state and changing information that is situated in a physical environment. Recommender systems can filter available information and provide learners with personalized and actionable suggestions that simplify their decision making while playing board games. Such recommendations can further be spatially aligned with relevant physical elements through Mixed Reality (MR). We present an MR system called GLAMRec for an engine-building strategy board game. GLAMRec provides personalized, transparent recommendations by integrating user data, real-time game state tracking, and ontology-based reasoning during a complex board game, which we use as a proxy environment for procedural learning tasks. We interviewed six board game designers to improve the GLAMRec and conducted a within-subjects design user study (N=32) to investigate how personalized explanations affect explanation satisfaction, user experience, and trust. We found that personalized recommendations significantly improve explanation satisfaction and hedonic user experience without affecting trust ratings, recommendation compliance, and game performance. These findings suggest that personalization primarily shaped perception of enjoyment rather than measurable learning outcomes or trust.

Conventional Mixed Reality (MR) workspaces are frequently organized in cockpit-like layouts, where multiple floating windows surround the user. While this configuration facilitates access to digital content, it often induces occlusion, reducing understanding of the physical environment and limiting access to real-world objects. To overcome this challenge, we present the Contour-Adaptive Mixed Environment Overlays (CAMEO), a contour-adaptive MR interface that drapes virtual windows onto physical surfaces. This design integrates digital content with nearby items, thereby improving users’ visual access to background objects and supporting interaction with them. We evaluate CAMEO in two controlled studies. The first demonstrates that draping reduces hand-movement detours relative to flat mid-air surfaces, enabling more direct interaction with nearby items. The second shows that controlled window deformation does not significantly impair text legibility when compared to flat surfaces. Together, these findings contribute a novel design paradigm for MR workspaces that balances immersion, readability, and environmental understanding.

Boundaries such as walls, windows, and doors are ubiquitous in the physical world, yet their potential in mixed reality (MR) remains underexplored. We present Unbounded, a Research through Design inquiry into object–boundary interaction (OBI). Building on prior work, we articulate a design space aimed at providing a shared language for OBI. To demonstrate its potential, we design and implement eight examples across productivity and art exploration scenarios, showcasing how OBIs can enrich and reframe everyday interactions. We further engage with six MR experts in one-on-one feedback sessions, using the design space and examples as design probes. Their reflections broaden the conceptual scope of OBI, reveal new possibilities for how the framework may be applied, and highlight implications for future MR interaction design.

Mixed Reality (MR) technologies are increasingly being used to enrich exhibitions and public spaces by blending digital content with the physical environment in real time. However, little is known about curatorial strategies for embedding MR exhibitions into public spaces or promoting audience experiences. To explore this, we designed and curated a campus-based MR art exhibition, using contextualism as the fundamental concept. We conducted an interdisciplinary expert focus group alongside exhibition viewing to identify opportunities, challenges, and design strategies from multiple perspectives. In parallel, we conducted user studies with general audiences to examine how curatorial strategies foster experiential qualities. Our findings reveal insights from both experts and general users along with strategies in curating MR exhibitions and highlight the foundational role of contextualism in curating MR art exhibitions in urban public spaces.

This paper investigates associations, explicit representations of relations between multiple views in Mixed Reality (MR). While research on 2D desktop environments offers extensive recommendations for communicating relations between multiple views, MR environments lack such systematic guidance, necessitating adapted solutions that consider their spatial affordances. To address this gap, we systematically explored association techniques in existing research. Building on established 2D multi-view literature and refining insights from prior design principles, we developed a codebook to describe view relations and their representations. Applying it to a corpus of 44 immersive multi-view approaches, we identified recurring design strategies and synthesized them into a design space of visual association techniques adapted for immersive contexts. Based on a lightweight prototyping framework, we validate the utility of the design space through three envisioning scenarios, demonstrating how associations can support exploration, coordination, and sensemaking in MR applications. Our results inform the design of MR multi-view environments.

Abstract Intelligent environments are rapidly gaining ground, propelled by a rich sensor infrastructure, the Internet of Things, sophisticated reasoning capabilities, and Artificial Intelligence. In this complex technological landscape, crafting usable intelligent environments and assessing the user experience (UX) demands a thorough understanding of the concepts involved and the parameters that need to be studied. This paper carries out a review of usability and UX evaluation methods and frameworks, elaborating on fundamental concepts and presenting in detail approaches and methods reported in the literature. It additionally examines evaluation approaches in adaptive and ubiquitous computing systems, which are closely associated with intelligent environments, and presents UX challenges and evaluation frameworks in intelligent environments. Finally, the findings are synthesized and consolidated to produce a comprehensive overview of the field and the challenges that lie ahead.

Current AI evaluation methods, which rely on static, model-only tests, fail to account for harms that emerge through sustained human-AI interaction. As AI systems proliferate and are increasingly integrated into real-world applications, this disconnect between evaluation approaches and actual usage becomes more significant. In this paper, we propose a shift towards evaluation based on interactional ethics, which focuses on interaction harms—issues like inappropriate parasocial relationships, social manipulation, and cognitive overreliance that develop over time through repeated interaction, rather than through isolated outputs. First, we discuss the limitations of current evaluation methods, which (1) are static, (2) assume a universal user experience, and (3) have limited construct validity. Drawing on research from human-computer interaction, natural language processing, and the social sciences, we present practical principles for designing interactive evaluations. These include ecologically valid interaction scenarios, human impact metrics, and diverse human participation approaches. Finally, we explore implementation challenges and open research questions for researchers, practitioners, and regulators aiming to integrate interactive evaluations into AI governance frameworks. This work lays the groundwork for developing more effective evaluation methods that better capture the complex dynamics between humans and AI systems.

The rapid development of virtual and augmented reality has highlighted the growing need for haptic feedback interfaces, particularly in portable or wearable formats. These haptic feedback interfaces significantly enhance the immersive experiences of users across various domains, including social media, gaming, biomedical instrumentation, and robotics by utilizing sophisticated actuators to stimulate somatosensory receptors or afferent nerves beneath the skin, thereby creating tactile sensations. Despite the progress in various haptic feedback interfaces that employ diverse working mechanisms, each mode has limitations. This article comprehensively reviews the current state and potential opportunities of various haptic feedback interfaces with a particular focus on actuator technologies. Existing haptic feedback interfaces can be classified into three main categories: force‐based haptic feedback interfaces, thermal haptic feedback interfaces, and electrotactile haptic feedback interfaces.

… Given the exceptional sensitivity and frequent use of the fingertips in tactile interaction, our framework prioritizes key haptic performance parameters specific to this region, including …

The rapid advancement in immersive metaverse technologies has accelerated the development of advanced haptic interface technologies designed to overcome the physical limitations of real‐world interactions. However, delivering high‐resolution tactile stimuli, such as vibrations, to mechanoreceptors and afferent nerves embedded deep within the multilayered skin remains a major challenge. The intrinsic skin barrier, mechanical mismatches between actuators and tissues, irregular skin contact, and limited stretchability continue to restrict stable and precise tactile perception. Recent progress has emphasized structural strategies tailored to specific body regions and the use of materials with skin‐like elasticity, which enhances conformability and enables more effective stimulation of subcutaneous sensory receptors. These advances highlight the potential of material and structural innovations for realizing more realistic tactile experiences. In this review, we provide a comprehensive overview of the historical evolution of haptic interfaces, systematically summarize the functional elements developed based on design and materials optimized for body‐specific requirements, and highlight representative case studies and integration strategies for skin‐attachable platforms. Finally, we discuss the technological pathways and persistent challenges that need to be addressed in realizing next‐generation haptic interfaces for a truly immersive metaverse.

… When the user, equipped with a VR headset, reaches out to touch a virtual object, our haptic interface provides a tactile response that simulates the sensation of physical contact. This is …

… haptic reproduction. In this article, we propose a thin, soft, dual-mode flexible tactile actuator that delivers high-fidelity haptic … tactile stimulation by force assistance in the force tactile …

Despite advances in vibrotactile displays, most existing systems are limited in their ability to deliver calibrated, frequency-differentiated stimulation across multiple touch modes. This constrains our understanding of how supra-threshold frequency modulation influences tactile perception, particularly in dynamic, shape-based interactions. To address this gap, we introduce the PinArray—a novel hybrid haptic device featuring a 4 × 3 array of independently actuated pins capable of delivering vibrations from 0 to 300 Hz. The PinArray uniquely supports static, passive, and active touch conditions, enabling nuanced exploration of tactile shape encoding. We evaluated the device in a user study examining the perception of edge-like shapes generated via frequency pairings. Results show that specific combinations, especially those involving static and dynamic frequency pairs, significantly enhance shape recognition. These findings highlight the device's potential for advancing both perceptual research and the development of expressive tactile interfaces.

Free-hand interaction in VR is intuitive and easy to learn, making it applicable to fundamental interactions such as VR typing. However, the absence of haptic feedback reduces spatial awareness and immersion while performing the input, impacting accuracy and increasing fatigue. While previous works embedded haptic feedback, they either require constant contact with the skin or a desktop installation with a fixed distance. We propose Ultraboard, a novel wearable haptic interface providing ultrasonic mid-air haptic feedback for all hand regions, including fingertips. We adaptively control the phased array's position in accordance with the hand movement and location to support consistent haptic feedback for real-time VR typing input. With simulation and experiment, we designed and validated the customized ultrasound phased array to support hand input. We propose guidelines for the development of a finger-level wearable ultrasonic mid-air haptics interface and system through this process. A follow-up user study showed significant improvements in typing confidence and usability with Ultraboard. Notably, the mid-air tactile typo alert enabled with our interface enhances user experience during VR typing. Our results showed a promising approach to utilizing a mid-air haptic interface to promote confidence in VR typing.

Haptic perception on touchscreens varies across fingers, yet little is known about how finger identity and multi-finger use shape tactile discrimination and user experience. We conducted two experiments with four haptic feedback. In Experiment 1, right-handed participants explored each of the ten fingers individually under stationary and moving conditions. Experiment 2 examined two-finger sequences with same participants. Results showed that moving exploration enhanced accuracy, confidence, and enjoyment, while stationary touch increased cognitive and physical load, especially for weaker fingers such as the left ring and pinky. The right thumb and index consistently performed best. In dual-finger trials, moving exploration improved second-finger performance, and adjacent same-hand pairs (e.g., Left Index–Left Thumb, Right Thumb–Right Index) yielded higher synergy. These findings highlight the role of finger anatomy, motion, and coordination, and provide concrete guidelines on which fingers (or combinations) and exploration modes to assign for haptic surfaces that optimize accuracy, comfort, and engagement.

… of brain-computer interface (BCI) technology with pseudohaptic … to operate 16 pseudo-haptic button configurations. Manifold … and experience of tactile illusions, presentation, actual …