The growing popularity of AI writing assistants creates exciting opportunities to support diverse writers. This study examines how personality shapes expectations for AI writing companions and how personality-informed design can enhance human–AI teaming in writing. Through exploratory co-design workshops with 24 writers representing different personality profiles, we elicited values and design ideas for AI writing companions spanning functionality, interaction dynamics, and visual representation. These insights informed two contrasting prototypes reflecting distinct writing orientations, used as design provocations in review-and-refinement workshops with eight participants to prompt reflection on fit, priorities, and writing practices. Our findings reveal both shared foundational needs across writers and meaningful personality-driven preferences that influence how writers engage with AI. This work underscores the importance of team matching in human-AI collaboration and demonstrates how aligning AI companions with individual cognitive and interpersonal needs can improve engagement and perceived collaboration effectiveness.

Most AI systems today are designed to manage tasks and execute predefined steps. This makes them effective for process coordination but limited in their ability to engage in joint problem-solving with humans or contribute new ideas. We introduce MultiColleagues, a multi-agent conversational system that shows how AI agents can act as colleagues by conversing with each other, sharing new ideas, and actively involving users in collaborative ideation processes. In a within-subjects study with 20 participants, we compared MultiColleagues to a single-agent baseline. Results show that MultiColleagues fostered stronger perceived social presence, and participants rated their outcomes as higher in quality and novelty, with more elaboration during ideation. These findings demonstrate the potential of AI agents to move beyond process partners toward colleagues that share intent, strengthen group dynamics, and collaborate with humans to advance ideas.

Knowing when to joke-and when not to-is a subtle skill often missing in large language models (LLMs).This study examines how well LLMs generate and recognize humor in emotionally sensitive, support-oriented conversations.We introduce two targeted datasets: one for evaluating humor generation across distinct styles, and another for testing humor and speaker role recognition in human-written supportive statements.Using GPT-4o, LLaMA3, and Gemini 1.5, we assess humor style alignment, emotional appropriateness, and role sensitivity.While models produce fluent and stylistically varied humor, they often struggle with contextual nuance and role interpretation.GPT-4o consistently performs best in tone alignment and emotional fit, but subtle humor types remain challenging across models.These results highlight current limitations in LLMs' pragmatic and relational understanding, underscoring the importance of human oversight in humor-sensitive applications.

IMPORTANCE: The study highlights the potential and limitations of the Large Language Models (LLMs) in recognizing different states of motivation to provide appropriate information for behavior change. Following the Transtheoretical Model (TTM), we identified the major gap of LLMs in responding to certain states of motivation through validated scenario studies, suggesting future directions of LLMs research for health promotion. OBJECTIVES: The LLMs-based generative conversational agents (GAs) have shown success in identifying user intents semantically. Little is known about its capabilities to identify motivation states and provide appropriate information to facilitate behavior change progression. MATERIALS AND METHODS: We evaluated 3 GAs, ChatGPT, Google Bard, and Llama 2 in identifying motivation states following the TTM stages of change. GAs were evaluated using 25 validated scenarios with 5 health topics across 5 TTM stages. The relevance and completeness of the responses to cover the TTM processes to proceed to the next stage of change were assessed. RESULTS: 3 GAs identified the motivation states in the preparation stage providing sufficient information to proceed to the action stage. The responses to the motivation states in the action and maintenance stages were good enough covering partial processes for individuals to initiate and maintain their changes in behavior. However, the GAs were not able to identify users' motivation states in the precontemplation and contemplation stages providing irrelevant information, covering about 20%-30% of the processes. DISCUSSION: GAs are able to identify users' motivation states and provide relevant information when individuals have established goals and commitments to take and maintain an action. However, individuals who are hesitant or ambivalent about behavior change are unlikely to receive sufficient and relevant guidance to proceed to the next stage of change. CONCLUSION: The current GAs effectively identify motivation states of individuals with established goals but may lack support for those ambivalent towards behavior change.

Little research has investigated the design of conversational styles of voice assistants (VA) for adults in their later adulthood with varying personalities. In this Wizard of Oz experiment, 34 middle-aged (50 to 64 years old) and 24 older adults (65 to 80 years old) participated in a user study at a simulated home, interacting with a VA using either formal or informal language. Older adults with higher agreeableness perceived VA as being more likable than middle-aged adults. Middle-aged adults showed similar technology acceptance toward the informal and formal VA, and older adults preferred using informal VA, especially those with low agreeableness. Further, while both middle-aged and older adults frequently anthropomorphized VAs by using human metaphors for them, older adults compared formal VA with professionals (e.g., librarians, teachers) and informal VA with their close ones (e.g., spouses, relatives). Overall, the conversational style showed differential effects on the perceptions of middle-aged and older adults, suggesting personalized design implications.

In this paper, we present Health Buddy, a voice agent integrated into commercially available Voice User Interfaces (VUIs) to support informal self-regulated learning (SRL) of health-related topics through multiple learning strategies and examine the efficacy of Health Buddy on learning outcomes for younger and older adults. We conducted a mixed-factorial-design experiment with 26 younger and 25 older adults, assigned to three SRL strategies (within-subjects): monologue, dialogue-based scaffolding building, and conceptual diagramming. We found that while younger adults benefit more from scaffolding building and conceptual diagramming, both younger and older adults showed equivalent learning outcomes. Furthermore, interaction fluency (operationalized by the number of conversational breakdowns) was associated with learning outcomes regardless of age. While older adults did not experience less fluent conversations, interaction fluency affected their technology acceptance toward VUIs more than younger ones. Our study discusses age-related learning differences and has implications for designing VUI-based learning programs for older adults.

Voice User Interfaces (VUIs) are popular among older adults, who find them easy to use and perceive them as social companions. However, there is a lack of research on voice-based applications to support physical activities for older adults. To address this gap, we present "Workout Pal," a voice agent designed to deliver physical activities to older adults. We conducted a mixed-methods study involving ten older adults to understand their perceptions and design priorities when interacting with Workout Pal. Questionnaires and semi-structured interviews were used to assess their experience, while experience-based co-design sessions facilitated collaboration in exploring the design space and identifying design requirements. Our findings highlight the feasibility and design preferences for smart speaker-based physical activity programs. The study contributes by sharing the design and development of Workout Pal, illustrating a novel co-design approach with older adults, and providing design implications tailored to the specific needs of older adults. The design guidelines emphasize the importance of sociability, voice design, and individualization. This research supports the development of elder-friendly VUIs helping older adults live independently and engage in physical activities.

In this study, we evaluated the ability of computational cognitive models of web‐navigation like CoLiDeS and CoLiDeS+ to model i) user interactions with search engines and ii) individual differences in search behavior due to variations in cognitive factors such as aging. CoLiDeS and CoLiDeS+ were extended to predict user clicks on search engine result pages. Their performance was evaluated using actual behavioral data from an experiment in which 2 types of information search tasks (simple vs. difficult), were presented to younger and older participants. The results showed that the model predictions matched significantly better with the actual user behavior on difficult tasks compared to simple tasks and with younger participants compared to older participants, especially for difficult tasks. Also, the matches were significantly better with CoLiDeS+ compared to CoLiDeS, especially for difficult tasks. We conclude that the advanced capabilities of CoLiDeS+, such as incorporating contextual information and implementing backtracking strategies enable it to predict user behavior significantly better than CoLiDeS, especially on difficult tasks. The usefulness of these modeling outcomes for the design of support systems for older adults is discussed.

An empirical study was conducted to investigate how older and younger users learned by performing exploratory search of health information using an interface that recommended relevant links based on browsing histories. While older and younger users gained both factual and structural knowledge about the health topics, significant age differences were observed. Our results showed that processing of recommended and regular Web links imposed distinct demands on cognitive abilities, which at least partially explained the observed age differences in the search process. The use of recommended links was positively associated with general knowledge, while the use of regular Web links was positively associated with processing capacity. Results also showed that the recommended links benefited both younger and older adults by broadening the exploration of information, which led to better learning. Implications on designs of health information interfaces that facilitate exploratory search and learning for different age groups were discussed.

We present results from an experiment that studied the information search behavior of younger and older adults in a medical decision-making task. To study how different combination of tasks and interfaces influenced search strategies and decision-making outcomes, we varied information structures of two interfaces and presented different task descriptions to participants. We found that younger adults tended to use different search strategies in different combination of tasks and interfaces, and older adults tended to use the same top-down strategies across conditions. We concluded that older adults were able to perform mental transformation of medical terms more effectively than younger adults. Thus older adults did not require changing strategies to maintain the same level of performance.

Previous research has shown that older adults performed worse in web search tasks, and attributed poorer performance to a decline in their cognitive abilities. We conducted a study involving younger and older adults to compare their web search behavior and performance in ill-defined and well-defined information tasks using a health information website. In ill-defined tasks, only a general description about information needs was given, while in well-defined tasks, information needs as well as the specific target information were given. We found that older adults performed worse than younger adults in well-defined tasks, but the reverse was true in ill-defined tasks. Older adults compensated for their lower cognitive abilities by adopting a top-down knowledge-driven strategy to achieve the same level of performance in the ill-defined tasks. Indeed, path models showed that cognitive abilities, health literacy, and knowledge influenced search strategies adopted by older and younger adults. Design implications are also discussed.