Autonomous agents powered by Large Language Models are transforming AI, creating an imperative for the visualization area. However, our field's focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such agentic visualization that preserve human agency while amplifying analytical capabilities. This paper addresses these questions by reinterpreting existing visualization systems with semi-automated or fully automatic AI components through an agentic lens. Based on this analysis, we extract a collection of design patterns for agentic visualization, including agentic roles, communication, and coordination. These patterns provide a foundation for future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.

We introduce DashSpace, a live collaborative immersive and ubiquitous analytics (IA/UA) platform designed for handheld and head-mounted Augmented/Extended Reality (AR/XR) implemented using WebXR and open standards. To bridge the gap between existing web-based visualizations and the immersive analytics setting, DashSpace supports visualizing both legacy D3 and Vega-Lite visualizations on 2D planes, and extruding Vega-Lite specifications into 2.5D. It also supports fully 3D visual representations using the Optomancy grammar. To facilitate authoring new visualizations in immersive XR, the platform provides a visual authoring mechanism where the user groups specification snippets to construct visualizations dynamically. The approach is fully persistent and collaborative, allowing multiple participants---whose presence is shown using 3D avatars and webcam feeds---to interact with the shared space synchronously, both co-located and remotely. We present three examples of DashSpace in action: immersive data analysis in 3D space, synchronous collaboration, and immersive data presentations.

We present drillboards, a technique for adaptive visualization dashboards consisting of a hierarchy of coordinated charts that the user can drill down to reach a desired level of detail depending on their expertise, interest, and desired effort. This functionality allows different users to personalize the same dashboard to their specific needs and expertise. The technique is based on a formal vocabulary of chart representations and rules for merging multiple charts of different types and data into single composite representations. The drillboard hierarchy is created by iteratively applying these rules starting from a baseline dashboard, with each consecutive operation yielding a new dashboard with fewer charts and progressively more abstract and simplified views. We also present an authoring tool for building drillboards and show how it can be applied to an agricultural dataset with hundreds of expert users. Our evaluation asked three domain experts to author drillboards for their own datasets, which we then showed to casual end-users with favorable outcomes.

Interactive visualization editors empower users to author visualizations without writing code, but do not provide guidance on the art and craft of effective visual communication. In this article, we explore the potential of using an off-the-shelf large language models (LLMs) to provide actionable and customized feedback to visualization designers. Our implementation, Visualizationary, demonstrates how ChatGPT can be used for this purpose through two key components: a preamble of visualization design guidelines and a suite of perceptual filters that extract salient metrics from a visualization image. We present findings from a longitudinal user study involving 13 visualization designers - 6 novices, 4 intermediates, and 3 experts - who authored a new visualization from scratch over several days. Our results indicate that providing guidance in natural language via an LLM can aid even seasoned designers in refining their visualizations.

We propose the notion of attention-aware visualizations (AAVs) that track the user's perception of a visual representation over time and feed this information back to the visualization. Such context awareness is particularly useful for ubiquitous and immersive analytics where knowing which embedded visualizations the user is looking at can be used to make visualizations react appropriately to the user's attention: for example, by highlighting data the user has not yet seen. We can separate the approach into three components: (1) measuring the user's gaze on a visualization and its parts; (2) tracking the user's attention over time; and (3) reactively modifying the visual representation based on the current attention metric. In this paper, we present two separate implementations of AAV: a 2D data-agnostic method for web-based visualizations that can use an embodied eyetracker to capture the user's gaze, and a 3D data-aware one that uses the stencil buffer to track the visibility of each individual mark in a visualization. Both methods provide similar mechanisms for accumulating attention over time and changing the appearance of marks in response. We also present results from a qualitative evaluation studying visual feedback and triggering mechanisms for capturing and revisualizing attention.

Comics are an effective method for sequential data-driven storytelling, especially for dynamic graphs - graphs whose vertices and edges change over time. However, manually creating such comics is currently time-consuming, complex, and error-prone. In this paper, we propose DG COMICS, a novel comic authoring tool for dynamic graphs that allows users to semi-automatically build and annotate comics. The tool uses a newly developed hierarchical clustering algorithm to segment consecutive snapshots of dynamic graphs while preserving their chronological order. It also presents rich information on both individuals and communities extracted from dynamic graphs in multiple views, where users can explore dynamic graphs and choose what to tell in comics. For evaluation, we provide an example and report the results of a user study and an expert review.

Onboarding a user to a visualization dashboard entails explaining its various components, including the chart types used, the data loaded, and the interactions available. Authoring such an onboarding experience is time-consuming and requires significant knowledge and little guidance on how best to complete this task. Depending on their levels of expertise, end users being onboarded to a new dashboard can be either confused and overwhelmed or disinterested and disengaged. We propose interactive dashboard tours (D-Tours) as semi-automated onboarding experiences that preserve the agency of users with various levels of expertise to keep them interested and engaged. Our interactive tours concept draws from open-world game design to give the user freedom in choosing their path through onboarding. We have implemented the concept in a tool called D-TOUR PROTOTYPE, which allows authors to craft custom interactive dashboard tours from scratch or using automatic templates. Automatically generated tours can still be customized to use different media (e.g., video, audio, and highlighting) or new narratives to produce an onboarding experience tailored to an individual user. We demonstrate the usefulness of interactive dashboard tours through use cases and expert interviews. Our evaluation shows that authors found the automation in the D-Tour Prototype helpful and time-saving, and users found the created tours engaging and intuitive.

We introduce Datamancer, a wearable device enabling bimanual gesture interaction across multi-display ubiquitous analytics environments. Datamancer addresses the gap in gesture-based interaction within data visualization settings, where current methods are often constrained by limited interaction spaces or the need for installing bulky tracking setups. Datamancer integrates a finger-mounted pinhole camera and a chest-mounted gesture sensor, allowing seamless selection and manipulation of visualizations on distributed displays. By pointing to a display, users can acquire the display and engage in various interactions, such as panning, zooming, and selection, using both hands. Our contributions include (1) an investigation of the design space of gestural interaction for physical ubiquitous analytics environments; (2) a prototype implementation of the Datamancer system that realizes this model; and (3) an evaluation of the prototype through demonstration of application scenarios, an expert review, and a user study.

AI's transformative impact on work, education, and everyday life makes it as much a political artifact as a technological one. Current AI models are opaque, centralized, and overly generic. The algorithmic automation they provide threatens human agency and democratic values in both workplaces and daily life. To confront such challenges, we turn to Scandinavian Participatory Design (PD), which was devised in the 1970s to face a similar threat from mechanical automation. In the PD tradition, technology is seen not just as an artifact, but as a locus of democracy. Drawing from this tradition, we propose Participatory AI as a PD approach to human-centered AI that applies five PD principles to four design challenges for algorithmic automation. We use concrete case studies to illustrate how to treat AI models less as proprietary products and more as shared socio-technical systems that enhance rather than diminish human agency, human dignity, and human values.

Consumer-level XR hardware now enables immersive spatial computing, yet most knowledge work remains confined to traditional 2D desktop environments. These worlds exist in isolation: writing emails or editing presentations favors desktop interfaces, while viewing 3D simulations or architectural models benefits from immersive environments. We address this fragmentation by combining spatial hypermedia, shareable dynamic media, and cross-reality computing to provide (1) composability of heterogeneous content and of nested information spaces through spatial transclusion, (2) pervasive cooperation across heterogeneous devices and platforms, and (3) congruent spatial representations despite underlying environmental differences. Our implementation, the Spatialstrates platform, embodies these principles using standard web technologies to bridge 2D desktop and 3D immersive environments. Through four scenarios---collaborative brainstorming, architectural design, molecular science visualization, and immersive analytics---we demonstrate how Spatialstrates enables collaboration between desktop 2D and immersive 3D contexts, allowing users to select the most appropriate interface for each task while maintaining collaborative capabilities.