Angela Zavaleta Bernuy

Runlong Ye, Naaz Sibia, Angela Zavaleta Bernuy et al. · utoronto

Systematic Literature Reviews (SLRs) are fundamental to scientific progress, yet the process is hindered by a fragmented tool ecosystem that imposes a high cognitive load. This friction suppresses the iterative, exploratory nature of scholarly work. To investigate these challenges, we conducted an exploratory design study with 20 experienced researchers. This study identified key friction points: 1) the high cognitive load of managing iterative query refinement across multiple databases, 2) the overwhelming scale and pace of publication of modern literature, and 3) the tension between automation and scholarly agency. Informed by these findings, we developed ARC, a design probe that operationalizes solutions for multi-database integration, transparent iterative search, and verifiable AI-assisted screening. A comparative user study with 8 researchers suggests that an integrated environment facilitates a transition in scholarly work, moving researchers from managing administrative overhead to engaging in strategic exploration. By utilizing external representations to scaffold strategic exploration and transparent AI reasoning, our system supports verifiable judgment, aiming to augment expert contributions from initial creation through long-term maintenance of knowledge synthesis.

Harsh Kumar, Suhyeon Yoo, Angela Zavaleta Bernuy et al.

Although engagement in self-directed wellness exercises typically declines over time, integrating social support such as coaching can sustain it. However, traditional forms of support are often inaccessible due to the high costs and complex coordination. Large Language Models (LLMs) show promise in providing human-like dialogues that could emulate social support. Yet, in-depth, in situ investigations of LLMs to support behavior change remain underexplored. We conducted two randomized experiments to assess the impact of LLM agents on user engagement with mindfulness exercises. First, a single-session study, involved 502 crowdworkers; second, a three-week study, included 54 participants. We explored two types of LLM agents: one providing information and another facilitating self-reflection. Both agents enhanced users' intentions to practice mindfulness. However, only the information-providing LLM, featuring a friendly persona, significantly improved engagement with the exercises. Our findings suggest that specific LLM agents may bridge the social support gap in digital health interventions.

Rita Garcia, Ellie Lovellette, Xi Wu et al.

Replication studies play an important role in Computing Education Research (CER) by supporting the development of consistent and reliable scientific knowledge. However, prior research indicates that the CER community tends to prioritise novel contributions over replication. A 2019 SLR identified only 54 replication studies among 2,269 papers published between 2009 and 2018 across five major CER venues. This study aims to examine how the landscape of replication research in CER has evolved since 2019. Specifically, we investigate whether the prevalence of replication studies has increased and explore current perceptions and experiences of CER researchers regarding replication. We replicated two prior studies. First, we conducted an updated SLR to identify replication studies published between 2019 and 2025 in the same five CER venues. Second, we replicated a survey of Computing Education researchers to better understand their perceptions, experiences, and challenges related to conducting and publishing replication studies. Our SLR identified 63 replication studies among 2,516 published papers. While the proportion of replication studies has increased slightly, overall growth remains limited. We observed a shift toward more published replication studies in journals and an increase in authors replicating their own prior work. Survey results indicate that although many researchers engage in replication within their teaching and research practice, they encounter significant challenges when attempting to publish replication studies. Despite increased discourse around open science and research rigour, the adoption of replication studies in CER has not substantially grown. Our findings offer opportunities for future research to promote replication and to explore how the CER community can encourage researchers to publish replication studies.