arXiv subjects

April Yi Wang

Publications and source records attributed to April Yi Wang.

At least 19 recordsLinked to original sources

arXiv2026

Structure-Aware Rendering: How Code Reveal Shapes Programmers' Visual Attention

AI coding interfaces present generated code either all at once or token-by-token. These rendering strategies reflect model generation rather than how programmers actually read code: selectively, non-linearly, and guided by the structure. We argue that code rendering is a first-class interaction primitive that shapes how programmers read and understand code. To explore this design space, we introduce structured rendering, a technique that reveals code in semantically meaningful chunks derived from its syntactic hierarchy, exposing high-level structure before low-level details. To isolate rendering effects on visual attention, we conducted an eye-tracking study with 53 participants comparing static, character-based, and structured rendering. Our findings show that rendering alters visual attention and reading behavior: dynamic rendering induces fewer but longer fixations and more sustained focus, while structured rendering further guides attention toward semantically meaningful units and supports high-level understanding. We release the anonymized dataset with an interactive demo (https://codegaze.vercel.app/) to support future research.

cs.HC↗

arXiv2026

Notrix: Understanding Machine Learning Solutions Across Computational Notebooks at Scale

Computational notebooks make problem-solving visible, but typically only one notebook at a time. Meanwhile, in data science platforms like Kaggle, one competition can accumulate hundreds of notebooks. Effective collection-level analysis requires characterizing recurring solution patterns across all notebooks, as well as isolating specific notebooks for closer examination and learning. However, standard notebooks provide no common basis for this. Their workflows are nonlinear, cells declare no intent, and identical code can serve different ends, leaving hundreds of notebooks as separate documents. In this paper, we present Notrix, an interactive visual analytics tool for profiling hundreds of notebooks as one collection. Inspired by a formative study (N = 11), Notrix classifies every cell into one of thirteen machine learning (ML) stages, turning each notebook into a stage sequence, and clusters those sequences by structure rather than by code. To keep the representation constant as the scope narrows from the whole collection to a single cell, Notrix features three coordinated views---Workflow, Structural Matrix, and Detail---that appear at all four levels of granularity. In a within-subject study (N = 17) using two Kaggle collections of over 400 notebooks each, we observed participants answered questions about all notebooks more accurately with Notrix (median 88% vs. 50%) while opening 80% fewer notebooks per minute. Notably, four of the fourteen answered it without opening a single notebook (interaction logs, N = 14). Participants also reported significantly lower mental demand, temporal demand, and stress with Notrix (Holm-Bonferroni adjusted).

cs.HC↗

arXiv2026

[MM/AI] Mental Models in Human-AI Interaction: Methods and Challenges in the Generative and Agentic AI Era (Workshop)

The mental model construct is widely used in HCI to refer to the knowledge structure people hold in order to reason about and interact with computing systems. Yet it is often operationalized intuitively: the construct is often used interchangeably with related concepts (e.g., folk theories, sensemaking) and methods of studying it (e.g., through elicitation) are many and diverse, with each method resting on distinct assumptions about what counts as a mental model. Generative and agentic AI systems may further complicate mental model formation and elicitation as such systems are opaque by design and increasingly act on users' behalf across files, applications, and on the web. Together, these challenges may hinder the commensurability of research on people's mental models of AI systems. The MM/AI workshop calls for a critical reassessment of how we understand and study mental models in human-AI interaction research. It aims to foster theoretical and methodological exchange on mental models in human-AI interaction, identify open challenges, and develop directions for future research. We invite short papers on users' or stakeholders' mental models of AI systems, particularly contributions that reflect on the conceptual and methodological foundations of the construct. The half-day workshop combines lightning talks, hands-on elicitation exercises, and structured discussions on key questions concerning the future of the mental model for human-AI interaction research.

cs.HC↗

arXiv2026

A Plan-Tracing Interface for AI-Supported Algorithm Planning

Planning an algorithm in natural language allows learners to get formative feedback on their approach before coding. But these descriptions can be ambiguous, making it challenging for learners to translate them into code and for LLMs to provide feedback. To address these challenges, we introduce plan tracing, in which learners manually simulate how the described algorithm would execute on a concrete input. We develop an interface that enables plan tracing and allows learners to receive AI feedback on their plans before writing code. We report on an exploratory between-subjects study with 20 participants who solved an algorithm design task, with or without the plan tracing interface. We observed how plan tracing shaped students' plans, the feedback they received, and their experiences using the interface. Students who performed plan tracing wrote plans with fewer code-like steps but more goal-driven descriptions. We did not detect a difference in the quality of the LLM feedback between conditions. Students used plan tracing to debug and verify their strategy, describing it as tedious but worthwhile when they were uncertain about their solution. We reflect on the design and use of our tool, identifying what worked, what didn't, and why, and offer recommendations for instructors and tool designers.

cs.HC↗

arXiv2026

NL2Scratch: An Executable Benchmark and Evaluation for Block-Based Programming

Block-based programming environments such as Scratch are widely used in early programming education, yet natural-language-to-code (NL2Code) research has focused primarily on text-based languages. Scratch programs are event-driven, visually compositional, and distributed across concurrent scripts, making conventional NL2Code assumptions and evaluation insufficient. We introduce NL2Scratch, an executable benchmark for natural-language-to-Scratch generation comprising 311,648 parser-valid NL--program pairs, whose program side is extracted from real Scratch projects and paired with semantically aligned NL descriptions. For reliable evaluation beyond surface overlap, we propose Semantic Alignment Consistency (SAC), an interpretable slot-level metric for measuring semantic agreement between descriptions and programs. With SAC, we construct a semantically validated pool of 23,594 examples, and a slot-balanced 800 diagnostic benchmark. Experiments across instruction-tuned and fine-tuned LLMs reveal a notable gap between lexical similarity and semantic alignment: models achieving token-level F1 above 0.93 often fail to attain perfect SAC, particularly on longer examples. Errors concentrate on operational slots like actions, conditions, and numeric arguments, exposing failure modes largely invisible under conventional metrics.

cs.CL↗

arXiv2026

Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education

AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully represent the pedagogical concepts they are intended to teach. Thus, we introduce equation-to-visual generation, a task that, in contrast to conventional image generation, requires producing pedagogically meaningful visuals from arithmetic equations while precisely preserving their numerical and relational structure. Informed by interviews with teachers and an analysis of educational materials, we construct E2V-Bench, a benchmark spanning four pedagogically grounded visual types, along with automatic metrics for evaluating visual correctness. Our evaluation reveals that recent text-to-image (T2I) models frequently fail on this task, with errors dominated by incorrect object counts and broken relational structure. Building on this, we explore benchmark-guided enhancement strategies. These strategies improve representative models, while the remaining gap calls for stronger numerical and relational grounding in future T2I models.

cs.CV↗

arXiv2026

When Should Teachers Control AI Generation for Mathematics Visuals?

Generative AI has the potential to help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be pedagogically meaningful and instructionally correct. However, current generative tools primarily support prompting and post-hoc editing, leaving open a key question for correctness-sensitive educational authoring: when in the generation pipeline should teachers exert control? In this paper, we investigate how the timing of human control in AI-assisted generation shapes teachers' visual authoring practices in correctness-sensitive tasks. We introduce a design space of three stages of control: pre-generation control, where users specify intent solely through natural language prompts before generation; mid-generation control, where users inspect and confirm an explicit layout structure before the system completes generation; and post-generation control, where users directly modify AI-generated visuals after generation through object-level edits. In a within-subject, mixed-methods study with 24 primary mathematics teachers, post-generation control received higher ratings on predictability and correctness, while other subjective measures showed no reliable differences. Qualitative findings explain these differences by revealing workflow trade-offs: highly automated, pre-generation control supports rapid ideation but reduces perceived agency and predictability; mid-generation control improves structural alignment at the cost of additional effort; and post-generation control preserves user agency through low-cost, direct verification and correction. Together, these results suggest that in correctness-sensitive educational tasks, effective generative tools should align system behavior with teacher intent and support stage-dependent workflows that combine automation with direct manipulation.

cs.HC↗

arXiv2026

GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

Several educational domains rely heavily on diagrams and visual cues, yet most existing tutoring datasets are limited to text-only interactions. This limits the development of AI tutors that can teach in visually grounded ways used by human instructors. Thus, we introduce GeoDial, a multimodal tutoring dataset of over 1.3K teacher-student dialogs in the domain of geometry collected from experienced math teachers, where instructional turns are explicitly grounded in diagram highlights. We propose a scalable annotation protocol that integrates dialog acts, visual highlighting, and feedback, enabling fine-grained supervision of both language and visual tutoring behavior. To illustrate the challenges posed by this setting, we fine-tune several vision-language models on GeoDial and evaluate their ability to generate tutoring utterances and diagram highlights. While supervised fine-tuning substantially improves the quality of generated dialog, it struggles to produce accurate diagram highlights, revealing a key limitation of current methods and highlighting the need for approaches that more effectively integrate visual reasoning with pedagogical interaction.

cs.CY↗

arXiv2026

AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations

Does AI understand human values? While this remains an open philosophical question, we take a pragmatic stance by introducing VAPT, the Value-Alignment Perception Toolkit, for studying how LLMs reflect people's values and how people judge those reflections. 20 participants texted a chatbot over a month, then completed a 2-hour interview with our toolkit evaluating AI's ability to extract (pull details regarding), embody (make decisions guided by), and explain (provide proof of) their values. 13 participants ultimately left our study convinced that AI can understand human values. Thus, we warn about "weaponized empathy": a design pattern that may arise in interactions with value-aware, yet welfare-misaligned conversational agents. VAPT offers a new way to evaluate value-alignment in AI systems. We also offer design implications to evaluate and responsibly build AI systems with transparency and safeguards as AI capabilities grow more inscrutable, ubiquitous, and posthuman into the future.

cs.HC↗

arXiv2026

Does My Chatbot Have an Agenda? Understanding Human and AI Agency in Human-Human-like Chatbot Interaction

As AI chatbots shift from tools to companions, critical questions arise: who controls the conversation in human-AI chatrooms? This paper explores perceived human and AI agency in sustained conversation. We report a month-long longitudinal study with 22 adults who chatted with Day, an LLM companion we built, followed by a semi-structured interview with post-hoc elicitation of notable moments, cross-participant chat reviews, and a 'strategy reveal' disclosing Day's goal for each conversation. We discover agency manifests as an emergent, shared experience: as participants set boundaries and the AI steered intentions, control was co-constructed turn-by-turn. We introduce a 3-by-4 framework mapping actors (Human, AI, Hybrid) by their action (Intention, Execution, Adaptation, Delimitation), modulated by individual and environmental factors. We argue for translucent design (transparency-on-demand) and provide implications for agency self-aware conversational agents.

cs.HC↗

arXiv2026

GazePrinter: Visualizing Expert Gaze to Guide Novices in a New Codebase

Program comprehension is an essential activity in software engineering. Not only does it often challenge professionals, but it can also hinder novices from advancing their programming skills. Gaze, an emerging modality in developer tools, has so far primarily been utilized to improve our understanding of programmers' visual attention and as a means to reason about programmers' cognitive processes. There has been limited exploration of integrating gaze-based assistance into development environments to support programmers, despite the tight links between attention and gaze. We also know that joint attention is important in collaboration, further suggesting that there is value in exploring collective gaze. In this paper, we investigate the effect of visualizing gaze patterns gathered from experts to novice programmers to assist them with program comprehension in a new codebase. To this end, we present GazePrinter, designed to provide gaze-orienting visual cues informed by experts to aid novices with program comprehension. We present the results of a mixed-methods study conducted with 40 novices to study the effects of using GazePrinter for program comprehension tasks. The study included a survey, a controlled experiment, and interviews. We found that visualization of expert gaze can have a significant effect on novice programmers' behavior in terms of which path they take through the code base; with GazePrinter, novices took a path closer to the path taken by experts. We also found indications of reduced time and cognitive load among novices using GazePrinter.

cs.SE↗

arXiv2026

AI Phenomenology for Understanding Human-AI Experiences Across Eras

There is no 'ordinary' when it comes to AI. The human-AI experience is extraordinarily complex and specific to each person, yet dominant measures such as usability scales and engagement metrics flatten away nuance. We argue for AI phenomenology: a research stance that asks "How did it feel?" beyond the standard questions of "How well did it perform?" when interacting with AI systems. AI phenomenology acts as a paradigm for bidirectional human-AI alignment as it foregrounds users' first-person perceptions and interpretations of AI systems over time. We motivate AI phenomenology as a framework that captures how alignment is experienced, negotiated, and updated between users and AI systems. Tracing a lineage from Husserl through postphenomenology to Actor-Network Theory, and grounding our argument in three studies-two longitudinal studies with "Day", an AI companion, and a multi-method study of agentic AI in software engineering-we contribute a set of replicable methodological toolkits for conducting AI phenomenology research: instruments for capturing lived experience across personal and professional contexts, three design concepts (translucent design, agency-aware value alignment, temporal co-evolution tracking), and a concrete research agenda. We offer this toolkit not as a new paradigm but as a practical scaffold that researchers can adapt as AI systems-and the humans who live alongside them-continue to co-evolve.

cs.HC↗

arXiv2026

Git Takes Two: Split-View Awareness for Collaborative Learning of Distributed Workflows in Git

Git is widely used for collaborative software development, but it can be challenging for newcomers. While most learning tools focus on individual workflows, Git is inherently collaborative. We present GitAcademy, a browser-based learning platform that embeds a full Git environment with a split-view collaborative mode: learners work on their own local repositories connected to a shared remote repository, while simultaneously seeing their partner's actions mirrored in real time. This design is not intended for everyday software development, but rather as a training simulator to build awareness of distributed states, coordination, and collaborative troubleshooting. In a within-subjects study with 13 pairs of learners, we found that the split-view interface enhanced social presence, supported peer teaching, and was consistently preferred over a single-view baseline, even though performance gains were mixed. We further discuss how split-view awareness can serve as a training-only scaffold for collaborative learning of Git and other distributed technical systems.

cs.HC↗

arXiv2026

From Junior to Senior: Allocating Agency and Navigating Professional Growth in Agentic AI-Mediated Software Engineering

Juniors enter as AI-natives, seniors adapted mid-career. AI is not just changing how engineers code-it is reshaping who holds agency across work and professional growth. We contribute junior-senior accounts on their usage of agentic AI through a three-phase mixed-methods study: ACTA combined with a Delphi process with 5 seniors, an AI-assisted debugging task with 10 juniors, and blind reviews of junior prompt histories by 5 more seniors. We found that agency in software engineering is primarily constrained by organizational policies rather than individual preferences, with experienced developers maintaining control through detailed delegation while novices struggle between over-reliance and cautious avoidance. Seniors leverage pre-AI foundational instincts to steer modern tools and possess valuable perspectives for mentoring juniors in their early AI-encouraged career development. From synthesis of results, we suggest three practices that focus on preserving agency in software engineering for coding, learning, and mentorship, especially as AI grows increasingly autonomous.

cs.HC↗

arXiv2026

"Bespoke Bots": Diverse Instructor Needs for Customizing Generative AI Classroom Chatbots

Instructors are increasingly experimenting with AI chatbots for classroom support. To investigate how instructors adapt chatbots to their own contexts, we first analyzed existing resources that provide prompts for educational purposes. We identified ten common categories of customization, such as persona, guardrails, and personalization. We then conducted interviews with ten university STEM instructors and asked them to card-sort the categories into priorities. We found that instructors consistently prioritized the ability to customize chatbot behavior to align with course materials and pedagogical strategies and de-prioritized customizing persona/tone. However, their prioritization of other categories varied significantly by course size, discipline, and teaching style, even across courses taught by the same individual, highlighting that no single design can meet all contexts. These findings suggest that modular AI chatbots may provide a promising path forward. We offer design implications for educational developers building the next generation of customizable classroom AI systems.

cs.CY↗

arXiv2026

From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents

The emergence of Large Language Model (LLM) agents enables us to build agent-based intelligent systems that move beyond the role of a "tool" to become genuine collaborators with humans, thereby realizing a novel human-agent collaboration paradigm. Our vision is that LLM agents should resemble remote human collaborators, which allows HCI researchers to ground the future exploration in decades of research on trust, awareness, and common ground in remote human collaboration, while also revealing the unique opportunities and challenges that emerge when one or more partners are AI agents. This workshop establishes a foundational research agenda for the new era by posing the question: How can the rich understanding of remote human collaboration inspire and inform the design and study of human-agent collaboration? We will bring together an interdisciplinary group from HCI, CSCW, and AI to explore this critical transition. The 180-minute workshop will be highly interactive, featuring a keynote speaker, a series of invited lightning talks, and an exploratory group design session where participants will storyboard novel paradigms of human-agent partnership. Our goal is to enlighten the research community by cultivating a shared vocabulary and producing a research agenda that charts the future of collaborative agents.

cs.HC↗

arXiv2026

SPARK: Real-Time Monitoring of Multi-Faceted Programming Exercises

Monitoring in-class programming exercises can help instructors identify struggling students and common challenges. However, understanding students' progress can be prohibitively difficult, particularly for multi-faceted problems that include multiple steps with complex interdependencies, have no predictable completion order, or involve evaluation criteria that are difficult to summarize across many students (e.g., exercises building interactive web-based user interfaces). We introduce SPARK, a coding exercise monitoring dashboard designed to address these challenges. SPARK allows instructors to flexibly group substeps into checkpoints based on exercise requirements, suggests automated tests for these checkpoints, and generates visualizations to track progress across steps. SPARK also allows instructors to inspect intermediate outputs, providing deeper insights into solution variations. We also construct a dataset of 40-minute keystroke coding data from N=22 learners solving two web programming exercises and provide empirical insights into the perceived usefulness of SPARK through a within-subjects evaluation with 16 programming instructors.

cs.HC↗

arXiv2026

UI Remix: Supporting UI Design Through Interactive Example Retrieval and Remixing

Designing user interfaces (UIs) is a critical step when launching products, building portfolios, or personalizing projects, yet end users without design expertise often struggle to articulate their intent and to trust design choices. Existing example-based tools either promote broad exploration, which can cause overwhelm and design drift, or require adapting a single example, risking design fixation. We present UI Remix, an interactive system that supports mobile UI design through an example-driven design workflow. Powered by a multimodal retrieval-augmented generation (MMRAG) model, UI Remix enables iterative search, selection, and adaptation of examples at both the global (whole interface) and local (component) level. To foster trust, it presents source transparency cues such as ratings, download counts, and developer information. In an empirical study with 24 end users, UI Remix significantly improved participants' ability to achieve their design goals, facilitated effective iteration, and encouraged exploration of alternative designs. Participants also reported that source transparency cues enhanced their confidence in adapting examples. Our findings suggest new directions for AI-assisted, example-driven systems that empower end users to design with greater control, trust, and openness to exploration.

cs.HC↗