Eye2Recall: Exploring Mixed-Initiative Reminiscence Activities via Gaze-Driven LLM Prompts for Older AdultsPhoto-based reminiscence can support well-being in older adults, yet most systems remain text-driven and offer little real-time adaptivity. We first conduct expert interviews to derive design considerations for accessibility, cultural fit, and safe emotional engagement. We then implemented Eye2Recall, an intelligent conversational interface that converts users’ gazes on old photos into mixed-initiative prompts for a large language model (LLM). We evaluated it in a pilot study with 12 older adults. Participants reported low-effort, smooth interactions, and perceived the agent’s questions as aligned with what they were looking at. Immediately after use, self-reported positive mood increased and negative mood decreased. Interviews further indicated that gaze-driven prompts helped retrieve concrete details and supported reflective storytelling. Our contribution is a concrete mechanism for gaze-to-prompt adaptivity that operationalizes mixed-initiative dialogue for older adults’ reminiscence experience.2026LHLei Han et al.Hong Kong University of Science and Technology (Guangzhou)Eye Tracking & Gaze InteractionHuman-LLM CollaborationElderly Care & Dementia SupportIUI
ESR-Coach: Leveraging Large Language Models for Training People to Provide Emotionally Supportive ResponsesEffectively providing emotional support is a critical yet intricate interpersonal skill. Supporters often lack accessible and practical training opportunities to develop this competency. To address this gap, we introduce ESR-Coach, a Large Language Model (LLM)-based coaching system designed to train individuals in emotionally supportive communication. ESR-Coach leverages multiple AI agents to generate practice scenarios, demonstrate reference responses, and provide assessments on user practice replies. We evaluate the proficiency of our system on these three tasks, demonstrating high-fidelity case generation, helpful exemplary responses, and valid response assessments. In our user study (N=20), ESR-Coach helped participants achieve an average improvement of 17% in response helpfulness. After training, participants also employed more diverse and effective strategies. We further discuss the social intelligence of LLMs and their potential to foster humans’ interpersonal skills in real-world scenarios.2026GJGongyao Jiang et al.The Hong Kong University of Science and Technology (Guangzhou)Human-LLM CollaborationAffective Human-Computer DialogueBehavior Change & Reflection TechnologyIUI
ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational InteractionsFrom purchasing a gift to deciding on a hobby, unfamiliar decisions---decisions without domain knowledge and experience---are frequent and significant. The complexity and uncertainty of such decisions demand unique approaches to information seeking, understanding, and decision-making. Our formative study highlights that in the current workflow, users want to start by discovering broad and relevant domain information evenly and simultaneously, quickly address emerging inquiries, and gain personalized standards to assess information found. We present ChoiceMates, an interactive multi-agent system designed to address these needs by enabling users to engage with a dynamic set of LLM agents each presenting a unique experience in the domain. Unlike existing multi-agent systems that automate tasks with agents, the user orchestrates agents to assist their decision-making process in each turn, through chatting with all agents, with a tagged subset of agents, or calling in new agents into the space. By comparing ChoiceMates with a web search condition and a multi-agent framework (n=12), we show that ChoiceMates enables a more confident, satisfactory decision-making with better situation understanding than web search, and higher decision quality than a commercial multi-agent framework. We further illustrate how participants utilized ChoiceMates to make unfamiliar decisions, providing insights into designing a more controllable and collaborative multi-agent system.2026JPJeongeon Park et al.University of California San DiegoHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationConversational ChatbotsIUI
DuoDrama: Supporting Screenplay Refinement Through LLM-Assisted Human ReflectionAI has been increasingly integrated into screenwriting practice. In refinement, screenwriters expect AI to provide feedback that supports reflection across the internal perspective of characters and the external perspective of the overall story. However, existing AI tools cannot sufficiently coordinate the two perspectives to meet screenwriters' needs. To address this gap, we present DuoDrama, an AI system that generates feedback to assist screenwriters' reflection in refinement. To enable DuoDrama, based on performance theories and a formative study with nine professional screenwriters, we design the Experience-Grounded Feedback Generation Workflow for Human Reflection (ExReflect). In ExReflect, an AI agent adopts an experience role to generate experience and then shifts to an evaluation role to generate feedback based on the experience. A study with fourteen professional screenwriters shows that DuoDrama improves feedback quality and alignment and enhances the effectiveness, depth, and richness of reflection. We conclude by discussing broader implications and future directions.2026YTYuying Tang et al.The Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Creative WritingCreative Collaboration & Feedback SystemsCHI
Agency-Enhanced Visual Search in VR: Robust to Distraction, Delay, and Perspective ShiftsThe sense of agency, the internal feeling of controlling one's actions and their outcomes, fundamentally shapes user interaction in virtual environments. Although extensively studied for its subjective impact, agency’s implicit yet critical role in guiding visual-spatial attention has been largely overlooked. This study investigated whether the sense of agency, conferred by prior active control, enhances subsequent visual search efficiency for the previously controlled stimulus under conditions of attentional, temporal, and spatial perturbation. Our results show that agency-driven attentional benefits are remarkably robust, persisting despite competing salient visual distractors, delayed outcomes, and changes in spatial layout. Furthermore, when a delay was introduced between the control and visual search, the agency effect attenuated for targets presented beyond the operators’ peripersonal space. These findings provide valuable insights for constructing immersive user experiences and advancing theoretical frameworks in human-computer interaction, suggesting efficient strategies to support sustained user engagement in virtual and augmented reality.2026CLChunlin Liao et al.Beijing Normal-Hong Kong Baptist UniversityImmersion & Presence ResearchSocial & Collaborative VREye Tracking & Gaze InteractionCHI
Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human OversightThe dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.2026JTJingyu Tang et al.University of Notre DameDark Patterns RecognitionHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationCHI
Hidden Labor behind the Hype: Understanding AI Side Hustles through Platform Narratives and Worker PracticesAI side hustles are increasingly promoted on social media as accessible, empowering, and profitable opportunities. This paper examines the gap between such platform narratives and workers' lived experiences through a mixed-method study of 7,938 RedNote posts and 16 semi-structured interviews. Our analysis identifies monetization typologies and rhetorical strategies that portray AI work as simple and rewarding, while interview data reveal hidden labor, unstable income, and the devaluation of human contributions. By juxtaposing platform narratives with lived experiences, we show how these narratives structurally foreground ease and reward while downplaying the precarity embedded in actual AI work. This study contributes a critical account of how AI side hustles are framed and experienced, and offers design implications for HCI: platforms should moderate promotional content and provide clearer risk communication, while designers of human–AI collaboration tools should highlight and value human input rather than allowing it to remain invisible.2026XYXiaoyu YANG et al.The Hong Kong University of Science and Technology (Guangzhou)AI Ethics, Fairness & AccountabilityAI-Assisted Decision-Making & AutomationParticipatory DesignCHI
Who Gets Written In? Gender, Identity, and Moderation in AO3’s Celebrity FanfictionArchive of Our Own (AO3) is a prominent fanfiction platform widely recognized for its feminist design ethos, with a commitment to inclusive, pluralism and community-driven content creation. Among the content on it, Real Person Fiction (RPF) --- creations based on public figures rather than fictional characters --- offers a unique lens into how users engage with identity, visibility, and cultural narratives. In this study, we conduct a large-scale computational analysis to examine gender representation, thematic diversity, and occupational portrayals. Our findings reveal a significant gender imbalance, with man characters disproportionately over-represented. The readers themselves are also often portrayed as sexual figures. Overall, the relationship portrayals tend to mirror occupational roles, incorporate sexual elements, and reconstruct gender tropes. We interrogate how these patterns intersect with authorship, identity, and power. This work contributes to ongoing conversations about equity, ethics, and feminist values in digital content ecosystems and feminist HCI development.2026PZPeixian Zhang et al.The Hong Kong University of Science and Technology (Guangzhou)Gender & Race Issues in HCITechnology Ethics & Critical HCISocial Platform Design & User BehaviorCHI
From Memory to Meaning: A Systematic Review of Reminiscence Technologies in HCITechnologies designed to support reminiscence, defined as the practice of engaging with one’s personal past, have become a significant area of inquiry within HCI. Although this has generated a diverse range of creative systems, the field still lacks a systematic account of the design principles that guide them. In this paper, we review 60 studies to examine both the psychosocial functions these technologies target and the mechanisms through which they operate. Our analysis suggests a predominant emphasis on positive identity construction and social connection, with comparatively less focus on functions related to everyday problem solving. To synthesize the mechanisms identified, we propose a cue-centered framework that treats mnemonic cues (e.g., photographs) as the basic unit of design. The framework organizes design mechanisms into a four-stage lifecycle: cue generation, augmentation, interaction, and sharing. It provides a conceptual vocabulary for analyzing reminiscence technologies and highlights underexplored opportunities for future research and design.2026ZZZhongyue Zhang et al.The Hong Kong University of Science and Technology (Guangzhou)Grief Support TechnologyTangible User Interface DesignPhysical-Digital Hybrid InteractionCHI
How Do We Evaluate Experiences in Immersive Environments?How do we evaluate experiences in immersive environments? Despite decades of research in immersive technologies such as virtual reality, the field remains fragmented. Studies rely on overlapping constructs, heterogeneous instruments, and little agreement on what counts as immersive experience. To better understand this landscape, we conducted a bottom-up scoping review of 375 papers published in ACM CHI, UIST, VRST, SUI, IEEE VR, ISMAR, and TVCG. Our analysis reveals that evaluation practices are often domain- and purpose-specific, shaped more by local choices than by shared standards. Yet this diversity also points to new directions. Instead of multiplying instruments, researchers benefit from integrating and refining them into smarter measures. Rather than focusing only on system outputs, evaluations must center the user’s lived experience. Computational modeling offers opportunities to bridge signals across methods, but lasting progress requires open and sustainable evaluation practices that support comparability and reuse. Ultimately, our contribution is to map current practices and outline a forward-looking agenda for immersive experience research.2026XLXiang Li et al.University of CambridgeImmersion & Presence ResearchPrototyping & User TestingComputational Methods in HCICHI
The Last Door You Open: A Mixed-Methods Study on Design Strategies for Positive Disengagement in Virtual Reality GamesDisengagement plays an important role in the overall game experience. However, extensive game research has focused on creating engaging experiences, whereas how players disengage remains insufficiently understood. Emerging studies have outlined characteristics of disengagement in screen-based video games. Little is known about how virtual reality (VR) shapes players’ disengagement process and what strategies might support positive disengagement experiences in VR games. Therefore, we conducted a co-design workshop (n = 18) and an online survey (n = 115) with VR game players. Our findings show that disengagement in VR games is often driven by factors such as physical discomfort and emotional overload. Participants adopt different disengagement strategies depending on the situation, such as restoring physical-world awareness to assist disengagement decisions. Then, we summarize three strategies for fostering positive disengagement experiences. Finally, we discuss these strategies, such as MR-based narrative space, extending the understanding of virtual-to-real transitions from a game experience perspective.2026ZWZiyan Wang et al.The Hong Kong University of Science and Technology (Guangzhou)Social & Collaborative VRImmersion & Presence ResearchGame UX & Player BehaviorCHI
RealTwin: Concept Graph Representation and Grounding Framework for Reality-Preserving Digital Twin ReconstructionReconstructing realistic digital twins has become crucial as advances in mixed reality, metaverse, and robotics demand more accurate simulations for the physical world. Despite technical progress, building high-fidelity digital twins from a systematic and human-centered perspective remains underexplored. Drawing from the human processing model, we decompose human-centric reality into perception, motion, and cognition, and define a reality-preserving digital twin (RPDT) as a reconstruction integrating these dimensions. We present RealTwin, an attribute-graph-based representation and inference framework for RPDT. Leveraging the grounding capabilities of Multimodal Large Language Models (MLLMs), RealTwin chains AI tools to construct attribute graphs that faithfully encode real-world properties. We validate RealTwin through both technical evaluation, showing promising success in graph parsing and attribute inference, and a user study, assessing its applicability across diverse user groups. Enlightened by RealTwin, we discuss critical issues, including ecology, interaction space, and real-world adoption, for future end-to-end, fine-grained, and scalable digital twin reconstruction.2026ZLZisu Li et al.The Hong Kong University of Science and TechnologyImmersion & Presence ResearchMixed Reality WorkspacesHuman-LLM CollaborationCHI
Orchid-Creator: An Authoring Tool Supporting LLM-Driven Interactive Narrative CreationLarge language models (LLMs) are reshaping interactive digital narratives (IDNs). However, creating complex interactive narratives while preserving narrative consistency remains challenging. We present Orchid‑Creator (Orchid), an LLM-based authoring tool that represents IDNs as story graphs with a card‑based interface for scene definition and conditional transitions. We evaluated Orchid in two studies: a usability study with eight authors, and a comparative study with 20 participants (authors, developers, and players) that compared Orchid to Twine and AI Dungeon. Authors reported that Orchid’s features met their needs (card‑based interface: 4.0/5; story graph: 4.38/5; variable setup: 4.5/5). Structuring narratives with Orchid was easier (M = 6.0/7, p < .01) and produced better‑structured stories (M = 5.3/7, p < .05) than the alternatives, balancing author control (M = 5.5/7) with outcome diversity (M = 5/7, p < .01) and maintaining comparable usability. Finally, a case study with an artist demonstrates Orchid’s utility for interactive art.2026ZWZhen Wu et al.HKUSTHuman-LLM CollaborationInteractive Narrative & Immersive StorytellingAI-Assisted Creative WritingCHI
DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent BehaviorsLarge language model (LLM)-based multi-agent systems have demonstrated impressive capabilities in handling complex tasks. However, the complexity of agentic behaviors makes these systems difficult to understand. When failures occur, developers often struggle to identify root causes and to determine actionable paths for improvement. Traditional methods that rely on inspecting raw log records are inefficient, given both the large volume and complexity of data. To address this challenge, we propose a framework and an interactive system, DiLLS, designed to reveal and structure the behaviors of multi-agent systems. The key idea is to organize information across three levels of query completion: activities, actions, and operations. By probing the multi-agent system through natural language, DiLLS derives and organizes information about planning and execution into a structured, multi-layered summary. Through a user study, we show that DiLLS significantly improves developers’ effectiveness and efficiency in identifying, diagnosing, and understanding failures in LLM-based multi-agent systems.2026RSRui Sheng et al.The Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationExplainable AI (XAI)CHI
Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI CollaborationFact verification is a critical yet underexplored component of non-litigation legal practice. While existing research has examined automation in legal workflow and human-AI collaboration in high-stakes domains, little is known about how GenAI can support fact verification, a task that demands prudent judgment and strict accountability. To address this, we conducted semi-structured interviews with 18 lawyers to understand their current verification practices, attitudes toward GenAI adoption, and expectations for future systems. We found that while lawyers use GenAI for low-risk tasks like drafting and language optimization, concerns over accuracy, confidentiality, and liability are currently limiting its adoption for fact verification. These concerns translate into core design requirements for AI systems that are trustworthy and accountable. Based on these, we contribute design insights for human-AI collaboration in legal fact verification, emphasizing the development of auditable systems that balance efficiency with professional judgment and uphold ethical and legal accountability in high-stakes practice.2026SHSirui Han et al.The Hong Kong University of Science and TechnologyHuman-LLM CollaborationExplainable AI (XAI)AI Ethics, Fairness & AccountabilityCHI
FingerBar: A Mid-Air Touch Bar Interface for Earphones Using Finger-Generated AcousticsCurrent touch-based interactions on earphones are limited by hygiene concerns and the small interaction surface. Recent works attempt to bypass these issues with mid-air gesture systems using active acoustic sensing. However, these signals may be audible and pose potential hearing risks. To address this, we propose FingerBar, a mid-air gesture recognition system for earphones that relies solely on microphones without active signal transmission. FingerBar leverages the distinctive friction sounds generated by finger gestures to achieve gesture recognition. We design a gesture filtering pipeline to maintain robustness against daily noise. An adversarial training strategy further enhances user-independent performance. From a set of 16 gestures, we identify the 7 most suitable for FingerBar based on user acceptability. Extensive evaluations demonstrate high accuracy and robustness. Furthermore, a user study confirms the practicality and acceptability of the system. Our findings highlight the promise of passive acoustic sensing as a user-friendly interaction modality for earphones.2026YZYankai Zhao et al.Southern University of Science and TechnologyMid-Air Haptics (Ultrasonic)Hand Gesture RecognitionSmartwatches & Fitness BandsCHI
Investigating How Physical Surfaces Can Serve as Common-Region Cues for Perceptual Grouping of Virtual Elements in Augmented RealityPerceptual grouping enables people to organize elements into units according to intrinsic (e.g., proximity) and extrinsic (e.g., common region) principles. However, the role of physical surfaces as extrinsic grouping cues for virtual elements in Augmented Reality (AR) remains unclear. To provide a deeper understanding, we conducted two within-subject studies. The first study (N = 24) using repetition discrimination tasks revealed that surfaces can be common-region cues in 3D, with their influence depending on their distance to target objects along the viewing direction. Building on these findings, the second study (N = 24) employed both objective and subjective measures to capture the interaction between proximity and common-region cues in AR. Results indicate that competing cues reduce group clarity. They also enable us to distill people's strategies for improving the clarity by leveraging their physical and virtual environments. Finally, we propose design recommendations for future AR systems in assisted grouping tasks.2026XYXuanhui Yang et al.The Hong Kong University of Science and TechnologyAR Navigation & Context AwarenessImmersion & Presence ResearchPrototyping & User TestingCHI
SituFont: A Just-in-Time Adaptive Intervention Interface for Enhancing Mobile Readability in Situational Visual ImpairmentsSituational visual impairments (SVIs) hinder mobile readability, causing discomfort and limiting information access. Building on prior work in adaptive typography and accessibility, this paper presents SituFont, a context-aware and human-in-the-loop adaptive typography adjustment approach that enhances smartphone mobile readability by dynamically adjusting font parameters based on real-time contextual changes. Using smartphone sensors and a human-in-the-loop approach, SituFont personalizes text presentation to accommodate personal factors (e.g., fatigue, distraction) and environmental conditions (e.g., lighting, motion, location). To inform its design, we conducted formative interviews (N=15) to identify key SVI factors and controlled experiments (N=18) to quantify their impact on optimal text parameters. A comparative user study (N=12) across eight simulated SVI scenarios demonstrated SituFont's effectiveness in improving smartphone mobile readability in terms of improved efficiency and reduced workload compared with a non-trivial manual adjustment baseline.2026JCJingruo Chen et al.Cornell UniversityMobile Accessibility DesignBehavior Change & Reflection TechnologyContext-Aware ComputingCHI
TableTale: Reviving the Narrative Interplay Between Tables and Text in Scientific PapersData tables play a central role in scientific papers. However, their meaning is often co-constructed with surrounding text through narrative interplay, making comprehension cognitively demanding for readers. In this work, we explore how interfaces can better support this reading process. We conducted a formative study that revealed key characteristics of text-table narrative interplay, including linking mechanisms, multi-granularity alignments, and mention typologies, as well as a layered framework of readers’ intents. Informed by these insights, we present TableTale, an augmented reading interface that enriches text with data tables at multiple granularities, including paragraphs, sentences, and mentions. TableTale automatically constructs a document-level linking schema within the paper and progressively renders cascade visual cues on text and tables that unfold as readers move through the text. A within-subject study with 24 participants showed that TableTale reduced cognitive workload and improved reading efficiency, demonstrating its potential to enhance paper reading and inform future reading interface design.2026LWLiangwei Wang et al.The Hong Kong University of Science and Technology (Guangzhou)Interactive Data VisualizationData StorytellingVisualization Perception & CognitionCHI
Friend, Foe, or Bot? Exploring Intergroup Dynamics in Hybrid Human-Bot TeamsExisting research has examined how artificial teammates influence collaboration within teams, but far less is known about their role in shaping interactions between teams. In particular, it remains unclear how transparent integration of AI teammates influences intergroup biases in competitive contexts. To investigate this, we designed StarHarvest, an online game where two hybrid teams (each consisting of one human and one bot, either concealed or revealed) competed for resources while bots elicited prosocial or antisocial behaviors. Drawing on data from 240 participants, we analyzed behavioral choices, evaluations, and resource allocations toward ingroup and outgroup members. Our findings show that hidden bots fostered stronger within-team coordination but also allowed asymmetric retribution toward weaker opponents. By contrast, revealed bots were treated as secondary teammates, reducing cohesion and shifting responsibility onto human partners. We conclude with design implications for socially responsible integration of artificial teammates, highlighting tensions between group-level and agent-level identities.2026AZAssem Zhunis et al.HKUSTHuman-Robot Collaboration (HRC)AI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityCHI