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
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
When LLMs Enter Everyday Feminism on Chinese Social Media: Opportunities and Risks for Women’s EmpowermentEveryday digital feminism refers to the ordinary, often pragmatic ways women articulate lived experiences and cultivate solidarity in online spaces. In China, such practices flourish on RedNote through discussions under hashtags like ''women's growth''. Recently, DeepSeek-generated content has been taken up as a new voice in these conversations. Given widely recognized gender biases in LLMs, this raises critical concerns about how LLMs interact with everyday feminist practices. Through an analysis of 430 RedNote posts, 139 shared DeepSeek responses, and 3211 comments, we found that users predominantly welcomed DeepSeek's advice. Yet feminist critical discourse analysis revealed that these responses primarily encouraged women to self-optimize and pursue achievements within prevailing norms rather than challenge them. By interpreting this case, we discuss the opportunities and risks that LLMs introduce for everyday feminism as a pathway toward women's empowerment, and offer design implications for leveraging LLMs to better support such practices.2026RZRunhua ZHANG et al.The Hong Kong University of Science and TechnologyAI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasGender & Race Issues in HCICHI
From Human Pragmatic Language Skills to Conversational Agent Design: A Systematic Review of Transfer StrategiesWhile conversational agents’ (CAs) semantic and syntactic capabilities have advanced, their pragmatic skills, using language appropriately in context, have emerged as a critical focus in practical applications. Hence, scholars integrate conversational skills derived from human-human interaction into CA designs. However, existing research mainly adopts an empirical approach and focuses on specific CA deployment, making it challenging to identify overarching patterns or develop a comprehensive methodology for transferring human pragmatic skills to CA design. Thus, we conducted a systematic review of 85 studies from primary databases (e.g., ACM, IEEE, etc.), focusing on designing CAs with human-derived conversational skills. We identified skill categories (verbal, paralinguistic, nonverbal), transfer strategies (from dialog data, theories, and via co-design), implementations, and evaluation metrics. We consolidated these insights into a four-stage design process: human skill exploration, definition, transfer, and iterative evaluation. Future research can leverage this to design CAs that achieve conversational goals through contextually appropriate language use.2026JHJiaxiong Hu et al.The Hong Kong University of Science and TechnologyAgent Personality & AnthropomorphismConversational ChatbotsUser Research Methods (Interviews, Surveys, Observation)CHI
InkIdeator: Supporting Chinese-Style Visual Design Ideation via AI-Infused Exploration of Chinese PaintingsVisual designers often seek inspiration from Chinese paintings when tasked with creating Chinese-style illustrations, posters, etc. Our formative study (N=10) reveals that during ideation, designers learn the cultural symbols, emotions, compositions, and styles in Chinese paintings but face challenges in searching, analyzing, and integrating these dimensions. This paper leverages multi-modal large models to annotate the value of each dimension in 16,315 Chinese paintings, built on which we propose InkIdeator, an ideation support system for Chinese-style visual designs. InkIdeator suggests cultural symbols associated with the task theme, provides dimensional keywords to help analyze Chinese paintings, and generates visual examples integrating user-selected keywords. Our within-subjects study (N=12) using a baseline system without extracted dimensional keywords, along with two extended use cases by Chinese painters, indicates InkIdeator’s effectiveness in creative ideation support, helping users efficiently explore cultural dimensions in Chinese paintings and visualize their ideas. We discuss implications for supporting culture-related visual design ideation with generative AI.2026SWShiwei Wu et al.Sun Yat-sen UniversityGenerative AI (Text, Image, Music, Video)Creative Collaboration & Feedback SystemsGraphic Design & Typography ToolsCHI
"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online DiscussionsAsynchronous online discussions enable diverse participants to co-construct knowledge beyond individual contributions. This process ideally evolves through sequential phases, from superficial information exchange to deeper synthesis. However, many discussions stagnate in the early stages. Existing AI interventions typically target isolated phases, lacking mechanisms to progressively advance knowledge co-construction, and the impacts of different intervention styles in this context remain unclear and warrant investigation. To address these gaps, we conducted a design workshop to explore AI intervention strategies (task-oriented and/or relationship-oriented) throughout the knowledge co-construction process, and implemented them in an LLM-powered agent capable of facilitating progression while consolidating foundations at each phase. A within-subject study (N=60) involving five consecutive asynchronous discussions showed that the agent consistently promoted deeper knowledge progression, with different styles exerting distinct effects on both content and experience. These findings provide actionable guidance for designing adaptive AI agents that sustain more constructive online discussions.2026YZYuanhao Zhang et al.Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationUser Research Methods (Interviews, Surveys, Observation)CHI
How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of ScreenwritersGenerative AI has greatly transformed creative work in various domains, such as screenwriting. To understand this transformation, prior research often focused on capturing a snapshot of human-AI co-creation practice at a specific moment, with less attention to how humans mobilize, regulate, and reflect to form the practice gradually. Motivated by Bandura's theory of human agency, we conducted a two-week study with 19 professional screenwriters to investigate how they embraced AI in their creation process. Our findings revealed that screenwriters not only mindfully planned, foresaw, and responded to AI usage, but, more importantly, through reflections on practice, they developed themselves and human-AI co-creation paradigms, such as cognition, strategies, and workflows. They also expressed various expectations for how future AI should better support their agency. Based on our findings, we conclude this paper with extensive discussion and actionable suggestions to screenwriters, tool developers, and researchers for sustainable human-AI co-creation.2026YTYuying Tang et al.The Hong Kong University of Science and TechnologyGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationCreative Collaboration & Feedback SystemsCHI
Exploring Aggressors’ In‑Match Cognitive and Emotional Formation and Toxic Behavior Trajectories in MOBA GamesToxic behavior in Multiplayer Online Battle Arena (MOBA) games has become a major issue. While previous studies have examined factors influencing toxic behavior, few have captured the cognitive and emotional states of the aggressors at the point of emergence of toxic behavior, or traced its evolution across an entire match. To fill the gap, we conducted replay-based semi-structured interviews with 18 players who recently initiated toxic behavior during matches. With adapted retrospective think-aloud protocols and players' emotional journey maps, we collected their subjective perceptions and dynamic changes of emotion. Through thematic analysis, we identified a multi-dimensional criterion for evaluating toxicity severity and a three-layer cognition–emotion association structure, and described recurring persistent and single-instance patterns of toxic behavior observed in our matches. Based on our findings, we contribute to understanding the internal evolution of player toxicity and discuss implications for preventive intervention strategies and designs aiming at mitigating toxic behavior2026KYKangyu Yuan et al.Hong Kong University of Science and TechnologyGame UX & Player BehaviorMultiplayer & Social GamesEmpathy & Emotional DesignCHI
Rethinking Technological Solutions for Community-Based Older Adult Care: Insights from `Older Partners' in ChinaAging in place refers to the enabling of individuals to age comfortably and securely within their own homes and communities. Continued community living creates a number of potential areas for design and, accordingly, various information and communication technologies have been employed to support older adult care. At the same time, human-led care services have been designed to support aging in place. Through a long-term ethnographic study that includes semi-structured interviews with 24 stakeholders, we consider these technology- and human-driven care infrastructures for aging in place, examining their origins, deployment, interactions with older adults, and challenges. In doing so, we reconsider the value of these different forms of older adult care, highlighting the various issues associated with using, for instance, health monitoring technology or appointment scheduling systems to care for older adults aging in place. We suggest that technology should take a ``supportive, not substitutive'' role in older adult care infrastructure and that designing for aging in place should not be synonymous with designing for independence but should, instead, consider the larger community and its dynamics.2025YSYuling Sun et al.Supporting Older Adults' CareCSCW
Exploring the Evolvement of User Engagement in Online Creative Community under the Surge of Generative AI: A Case Study of DeviantArtThe rise of AI-generated content (AIGC) is transforming online creative communities (OCCs) and posing challenges to their regulation. The interacting behaviors, such as sharing artworks with descriptions, commenting on creations, and creators’ subsequent replying are the essential components of user engagement in these communities. Understanding the influence of AIGC on the evolving user engagement could be helpful for community regulation. In this work, we collect 235K posts and their associated 255K comments from DeviantArt, a large creative community allowing uploading AIGC. Through open coding, we identify five categories of practices in describing and commenting on artworks, respectively. A set of deep learning models are applied to classify the posts and comments. We then combine time series regression analysis, causal inference analysis, and logistic regression analysis, to examine the impact of the surge of AIGC on user engagement. Results suggest that AI-generated artworks show a decreasing emphasis on the content of creations but an increasing trend toward commercial and promotion purposes. AI-generated artworks emphasize less on IP issues than human-created ones, while the awareness of IP issues drops for human-created artworks with the growth of AIGC as well. Although comments with high sentiment valence, for peer bonding or for requesting usage positively predict the reply behavior for human-created artworks, community members are less likely to maintain these interactions as AIGC rises. Finally, we discuss insights and design implications for OCCs.2025QGQingyu Guo et al.User Experiences in Online CommunitiesCSCW
When Traditional Medicine Meets AI: Critical Considerations for AI-Empowered Clinical Support in Traditional MedicineTraditional Medicine (TM) is the oldest healthcare form and has been increasingly adopted as the primary or complementary medical therapy in the world. However, TM’s practical development remains highly challenging. While AI has become powerful in advancing modern medicine, limited attention has been paid to its potential and usage in TM. This study addressed this gap through a probe-based interview study with 16 TM clinicians, examining their experiences, perceptions, and expectations of AI-empowered clinical support systems. Our findings revealed that despite numerous AI-CDS systems, their practical usage in TM settings was still limited. We identified a series of practical challenges when integrating AI-CDS into TM clinical scenarios, largely due to TM’s unique features and the significant data work challenges these features present. We end by critically discussing the potential issues that may arise when integrating AI into practical TM scenarios, and proposing a series of practical recommendations for future studies.2025YSYuling Sun et al.AI-Assisted HealthcareCSCW
PaperBridge: Crafting Research Narratives through Human-AI Co-ExplorationResearchers frequently need to synthesize their own publications into coherent narratives that demonstrate their scholarly contributions. To suit diverse communication contexts, exploring alternative ways to organize one’s work while maintaining coherence is particularly challenging, especially in interdisciplinary fields like HCI where individual researchers' publications may span diverse domains and methodologies. In this paper, we present PaperBridge, a human–AI co-exploration system informed by a formative study and content analysis. PaperBridge assists researchers in exploring diverse perspectives for organizing their publications into coherent narratives. At its core is a bi-directional analysis engine powered by large language models, supporting iterative exploration through both top-down user intent (e.g., determining organization structure) and bottom-up refinement on narrative components (e.g., thematic paper groupings). Our user study (N=12) demonstrated PaperBridge's usability and effectiveness in facilitating the exploration of alternative research narratives. Our findings also provided empirical insights into how interactive systems can scaffold academic communication tasks.2025RZRunhua ZHANG et al.Human-LLM CollaborationData StorytellingComputational Methods in HCIUIST
InteRecon: Towards Reconstructing Interactivity of Personal Memorable Items in Mixed RealityDigital capturing of memorable personal items is a key way to archive personal memories. Although current digitization methods (e.g., photos, videos, 3D scanning) can replicate the physical appearance of an item, they often cannot preserve its real-world interactivity. We present Interactive Digital Item (IDI), a concept of reconstructing both the physical appearance and, more importantly, the interactivity of an item. We first conducted a formative study to understand users' expectations of IDI, identifying key physical interactivity features, including geometry, interfaces, and embedded content of items. Informed by these findings, we developed InteRecon, an AR prototype enabling personal reconstruction functions for IDI creation. An exploratory study was conducted to assess the feasibility of using InteRecon and explore the potential of IDI to enrich personal memory archives. Results show that InteRecon is feasible for IDI creation, and the concept of IDI brings new opportunities for augmenting personal memory archives.2025ZLZisu Li et al.The Hong Kong University of Science and Technology, IIP (Computational Media and Arts); MIT CSAILInteractive Narrative & Immersive StorytellingCHI
"AI Afterlives" as Digital Legacy: Perceptions, Expectations, and ConcernsThe rise of generative AI technology has sparked interest in using digital information to create AI-generated agents as digital legacy. These agents, often referred to as "AI Afterlives", present unique challenges compared to traditional digital legacy. Yet, there is limited human-centered research on "AI Afterlife" as digital legacy, especially from the perspectives of the individuals being represented by these agents. This paper presents a qualitative study examining users' perceptions, expectations, and concerns regarding AI-generated agents as digital legacy. We identify factors shaping people's attitudes, their perceived differences compared with the traditional digital legacy, and concerns they might have in real practices. We also examine the design aspects throughout the life cycle and interaction process. Based on these findings, we situate "AI Afterlife" in digital legacy, and delve into design implications for maintaining identity consistency and balancing intrusiveness and support in "AI Afterlife" as digital legacy.2025YLYing Lei et al.Simon Fraser University, School of Interactive Arts and TechnologyGenerative AI (Text, Image, Music, Video)Online Identity & Self-PresentationCHI
Characterizing LLM-Empowered Personalized Story Reading and Interaction for Children: Insights From Multi-Stakeholders' PerspectivePersonalized interaction is highly valued by parents in their story-reading activities with children. While AI-empowered story-reading tools have been increasingly used, their abilities to support personalized interaction with children are still limited. Recent advances in large language models (LLMs) show promise in facilitating personalized interactions, but little is known about how to effectively and appropriately use LLMs to enhance children's personalized story-reading experiences. This work explores this question through a design-based study. Drawing on a formative study, we designed and developed StoryMate, an LLM-empowered personalized interactive story-reading tool for children, following an empirical study with children, parents, and education experts. Our participants valued the personalized features in StoryMate, and also highlighted the need to support personalized content, guiding mechanisms, reading context variations, and interactive interfaces. Based on these findings, we propose a series of design recommendations for better using LLMs to empower children's personalized story reading and interaction.2025JCJiaju Chen et al.East China Normal UniversityHuman-LLM CollaborationEarly Childhood Education TechnologyInteractive Narrative & Immersive StorytellingCHI
JournalAIde: Empowering Older Adults in Digital Journal WritingDigital journaling offers a means for older adults to express themselves, document their lives, and engage in self-reflection, contributing to the maintenance of cognitive function and social connectivity. Although previous works have investigated the motivations and benefits of digital journaling for older adults, little technical support has been designed to offer assistance. We conducted a formative study with older adults and uncovered their encountered challenges and preferences for technical support. Informed by the findings, we designed a Large Language Model (LLM) empowered tool, JournalAIde, which provides vicarious experience, idea organization, sample text generation, and visual editing cues to enhance older adults’ confidence, writing ability, and sustained attention during digital journaling. Through a between-subjects study and a field deployment, we demonstrated the JournalAIde’s significant effectiveness compared to a baseline system in empowering older adults in digital journaling. We further investigated older adults' experiences and perceptions of LLM writing assistance.2025SZShixu Zhou et al.The Hong Kong University of Science and Technology (Guangzhou); Hong Kong University of Science and TechnologyHuman-LLM CollaborationAging-Friendly Technology DesignAI-Assisted Creative WritingCHI
Scaffolded Turns and Logical Conversations: Designing Humanized LLM-Powered Conversational Agents for Hospital Admission InterviewsHospital admission interviews are critical for patient care but strain nurses' capacity due to time constraints and staffing shortages. While LLM-powered conversational agents (CAs) offer automation potential, their rigid sequencing and lack of humanized communication skills risk misunderstandings and incomplete data capture. Through participatory design with clinicians and volunteers, we identified essential communication strategies and developed a novel CA that implements these strategies through: (1) dynamic topic management using graph-based conversation flows, and (2) context-aware scaffolding with few-shot prompt tuning. Technical evaluation on an admission interview dataset showed our system achieving performance comparable to or surpassing human-written ground truth, while outperforming prompt-engineered baselines. A between-subject study (N=44) demonstrated significantly improved user experience and data collection accuracy compared to existing solutions. We contribute a framework for humanizing medical CAs by translating clinician expertise into algorithmic strategies, alongside empirical insights for balancing efficiency and empathy in healthcare interactions, and considerations for generalizability.2025DLDingdong Liu et al.The Hong Kong University of Science and TechnologyConversational ChatbotsHuman-LLM CollaborationCHI
Signaling Human Intentions to Service Robots: Understanding the Use of Social Cues during In-Person ConversationsAs social service robots become commonplace, it is essential for them to effectively interpret human signals, such as verbal, gesture, and eye gaze, when people need to focus on their primary tasks to minimize interruptions and distractions. Toward such a socially acceptable Human-Robot Interaction, we conducted a study (N=24) in an AR-simulated context of a coffee chat. Participants elicited social cues to signal intentions to an anthropomorphic, zoomorphic, grounded technical, or aerial technical robot waiter when they were speakers or listeners. Our findings reveal common patterns of social cues over intentions, the effects of robot morphology on social cue position and conversational role on social cue complexity, and users' rationale in choosing social cues. We offer insights into understanding social cues concerning perceptions of robots, cognitive load, and social context. Additionally, we discuss design considerations on approaching, social cue recognition, and response strategies for future service robots.2025HLHanfang Lyu et al.Hong Kong University of Science and TechnologySocial Robot InteractionHuman-Robot Collaboration (HRC)CHI
Understanding Screenwriters' Practices, Attitudes, and Future Expectations in Human-AI Co-CreationWith the rise of AI technologies and their growing influence in the screenwriting field, understanding the opportunities and concerns related to AI's role in screenwriting is essential for enhancing human-AI co-creation. Through semi-structured interviews with 23 screenwriters, we explored their creative practices, attitudes, and expectations in collaborating with AI for screenwriting. Based on participants' responses, we identified the key stages in which they commonly integrated AI, including story structure and plot development, screenplay text, goal and idea generation, and dialogue. Then, we examined how different attitudes toward AI integration influence screenwriters' practices across various workflow stages and their broader impact on the industry. Additionally, we categorized their expected assistance using four distinct roles of AI: actor, audience, expert, and executor. Our findings provide insights into AI's impact on screenwriting practices and offer suggestions on how AI can benefit the future of screenwriting.2025YTYuying Tang et al.Hong Kong University of Science and Technology , Academy of Interdisciplinary StudiesHuman-LLM CollaborationAI-Assisted Creative WritingCHI