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.
Designing project-based learning (PBL) demands managing highly interdependent components, a task that both traditional linear tools and purely conversational AI struggle with. Traditional tools fail to capture the non-linear nature of creative design, while conversational systems lack the persistent, shared context necessary for reflective collaboration. Grounded in theories of distributed cognition, we introduce CoMAP, a system that embodies a graph-based collaboration paradigm. By providing a shared visual workspace with dual-modality AI support, CoMAP transforms the human-AI relationship from a prompt-and-response loop into a transparent and equitable partnership. Our study with 30 educators shows CoMAP significantly improves teachers' design expression, divergent thinking, and iterative practice compared to a dialogue-only baseline. These findings demonstrate how a nonlinear, artifact-centric approach can foster trust, reduce cognitive load, and support educators to take control of their creative process. Our contributions are available at: https://comap2025.github.io/
Educational videos are widely used, but accessibility guidelines beyond captions for d/Deaf and Hard-of-Hearing (DHH) learners remain limited. Mayer's multimedia learning theory assumes visual-auditory dual-channel processing, yet DHH learners with limited access to the auditory channel have distinct visual abilities and cognitive demands. This paper introduces motion-driven design ideas to support cognitive processing and improve video-based learning for DHH learners. Through a three-phase study, we identified four key challenges—such as misaligned content and visual overload—and proposed four design ideas that extend multimedia learning theory. We then evaluated these ideas with 16 DHH learners and 6 experts in Deaf education. The results show that motion-driven approaches reduce misalignment, ease visual attention switching, and improve the integration of visual and textual information across video types. For example, guiding visual attention switching minimizes confusion in complex visual contexts, such as programming demonstrations, while using relevant visuals enriches talking-head videos with graphics to clarify abstract ideas in captions. More research is needed to develop these promising ideas into well-defined principles.
Disabled and neurodivergent LGBTQIA+ individuals often co-create adaptive communication practices within their romantic partnerships; however, little is known about how these strategies evolve over time. We present findings from a diary and co-design study with five disabled LGBTQIA+ partnerships, documenting how communication is negotiated and sustained through shifting relational, emotional, and access needs. We argue that this ongoing work constitutes a relational infrastructure—the communicative system of shared practices, adaptive routines, and negotiated meanings that disabled and neurodivergent LGBTQIA+ partners co-create to navigate their shared lives. To model these dynamics, we introduce the Relational Access Framework for Communication (RAF-Comm): A Model for Disabled and Neurodivergent LGBTQIA+ Partnerships, a provisional and generative framework that centers identity, co-creation, and adaptation as fundamental to relational accessibility. Our findings highlight the conditional use of technology and the importance of non-use as a valid, relationship-preserving choice. We conclude with design implications for technologies that support the personal, continuously evolving ecosystems of care these partnerships create for themselves.
Foundation models are predominantly trained on English-language and Western-centric data, often marginalizing non-English contexts. While recent scholarship calls for more localized models, there remains limited empirical research on how such models are developed and deployed. This paper examines the sociotechnical dynamics of local model development and deployment in South Korea, where efforts to build “sovereign AI” reflect aspirations for greater autonomy over data, infrastructure, and cultural alignment. Drawing on semi-structured interviews with 15 Korean AI practitioners, we surface key motivations, such as linguistic and cultural specificity, regulatory compliance, and reduced dependence on foreign technologies, that are entangled with broader imaginaries of sovereignty. At the same time, these efforts face constraints including limited GPU access, scarcity of Korean-language data, and reliance on global infrastructures. We argue that AI sovereignty should be understood not as an abstract political principle but as situated practices shaped by opportunities and constraints of local sociotechnical and regulatory contexts.
Designing adaptive tutoring systems for software learning presents challenges in determining appropriate instructional modalities. To inform the design of such systems, we conducted an observational study of ten human teacher-student pairs (N=20), where experienced design software users taught novices two new graphic design software features through multi-step procedures. These lessons were limited to three communication channels (speech, visual annotations, and remote screen control) to mimic possible AI tutor modalities. We found that annotations complement speech with spatial precision and remote control complements it with spatial and temporal precision but both of them cause intrusion to learner agency. Teachers adaptively select modalities to balance the need for instruction progress with students' cognitive engagement and sense of digital territory ownership. Our results provide further support to the contiguity principles and the value of agency in learning, while suggesting precision-agency trade-off and digital territoriality as new design constraints for adaptive software guidance.
Collaborative problem solving (CPS) is a fundamental practice in middle-school mathematics education; however, student groups frequently stall or struggle without ongoing teacher support. Recent work has explored how Generative AI tools can be designed to support one-on-one tutoring, but little is known about how AI can be designed as peer learning partners in collaborative learning contexts. We conducted a participatory design study with 24 middle school students, who first engaged in mathematics CPS tasks with AI peers in a technology probe, and then collaboratively designed their ideal AI peer. Our findings reveal that students envision an AI peer as competent in mathematics yet explicitly deferential, providing progressive scaffolds such as hints and checks under clear student control. Students preferred a tone of friendly expertise over exaggerated personas. We also discuss design recommendations and implications for AI peers in middle school mathematics CPS.